Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3243 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 12.3032. Min Range: -12.3032
Max Act: 12.3032. Min Act: -0.1700
Data Index: 4067784 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3032. Min Range: -12.3032
Max Act: 12.1782. Min Act: -0.1700
Data Index: 7454069 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.9907. Min Act: -0.1700
Data Index: 4637315 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.9907. Min Act: -0.1700
Data Index: 1756664 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.8657. Min Act: -0.1700
Data Index: 5095704 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.8657. Min Act: -0.1700
Data Index: 6566942 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.8032. Min Act: -0.1700
Data Index: 3268228 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.6782. Min Act: -0.1700
Data Index: 7968568 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.7407. Min Act: -0.1700
Data Index: 8767597 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.6782. Min Act: -0.1700
Data Index: 7160162 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.5532. Min Act: -0.1700
Data Index: 5021435 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.5532. Min Act: -0.1700
Data Index: 2685813 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.4907. Min Act: -0.1700
Data Index: 6450730 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.6157. Min Act: -0.1700
Data Index: 5067660 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.5532. Min Act: -0.1700
Data Index: 1850413 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.5532. Min Act: -0.1700
Data Index: 4254116 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.5532. Min Act: -0.1700
Data Index: 6354792 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.5532. Min Act: -0.1700
Data Index: 569229 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.4282. Min Act: -0.1700
Data Index: 1069948 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3032. Min Range: -12.3032
Max Act: 11.4907. Min Act: -0.1700
Data Index: 8041035 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19