Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.6911. Min Act: -0.1700
Data Index: 2978706 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.5661. Min Act: -0.1700
Data Index: 8546044 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.5349. Min Act: -0.1700
Data Index: 3433219 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.4411. Min Act: -0.1700
Data Index: 234096 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.4411. Min Act: -0.1700
Data Index: 6971937 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.4724. Min Act: -0.1700
Data Index: 8180491 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.3786. Min Act: -0.1700
Data Index: 1833588 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.3161. Min Act: -0.1700
Data Index: 6975148 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.3161. Min Act: -0.1700
Data Index: 3101855 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.3474. Min Act: -0.1700
Data Index: 4963888 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.3161. Min Act: -0.1700
Data Index: 589149 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.2224. Min Act: -0.1700
Data Index: 8178374 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.2536. Min Act: -0.1700
Data Index: 5089849 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.2536. Min Act: -0.1700
Data Index: 2284625 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.2536. Min Act: -0.1700
Data Index: 7518632 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.2536. Min Act: -0.1700
Data Index: 4826420 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.1911. Min Act: -0.1700
Data Index: 5353302 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.1911. Min Act: -0.1700
Data Index: 4920304 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.1599. Min Act: -0.1700
Data Index: 7050452 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6911. Min Range: -6.6911
Max Act: 6.1286. Min Act: -0.1700
Data Index: 8096254 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19