Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1006 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.5067. Min Act: -0.1700
Data Index: 8178449 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.4364. Min Act: -0.1697
Data Index: 7564536 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.4364. Min Act: -0.1697
Data Index: 8218335 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.4276. Min Act: -0.1700
Data Index: 1032990 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.4188. Min Act: -0.1700
Data Index: 7903553 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.4100. Min Act: -0.1700
Data Index: 7149047 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.4012. Min Act: -0.1700
Data Index: 7460770 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.4012. Min Act: -0.1700
Data Index: 521370 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3747. Min Act: -0.1700
Data Index: 5749977 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3747. Min Act: -0.1699
Data Index: 981855 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3483. Min Act: -0.1700
Data Index: 30450 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3747. Min Act: -0.1688
Data Index: 2386894 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3571. Min Act: -0.1700
Data Index: 7263034 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3571. Min Act: -0.1700
Data Index: 953027 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3483. Min Act: -0.1700
Data Index: 4470378 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3571. Min Act: -0.1700
Data Index: 23250 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3483. Min Act: -0.1700
Data Index: 3491915 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3571. Min Act: -0.1696
Data Index: 6497693 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3659. Min Act: -0.1700
Data Index: 3478092 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5067. Min Range: -1.5067
Max Act: 1.3395. Min Act: -0.1700
Data Index: 4224322 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19