Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3234. Min Range: -7.3234
Max Act: 7.3234. Min Act: -0.1700
Data Index: 4673218 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.9484. Min Act: -0.1700
Data Index: 1696892 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.7921. Min Act: -0.1700
Data Index: 5856510 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.6984. Min Act: -0.1700
Data Index: 6316998 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.6671. Min Act: -0.1700
Data Index: 7660044 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.6046. Min Act: -0.1700
Data Index: 6416610 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.5421. Min Act: -0.1700
Data Index: 2655941 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.5109. Min Act: -0.1700
Data Index: 8811047 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.4796. Min Act: -0.1700
Data Index: 8658980 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.4484. Min Act: -0.1700
Data Index: 1623776 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.4484. Min Act: -0.1700
Data Index: 3226483 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.4171. Min Act: -0.1700
Data Index: 89257 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.4171. Min Act: -0.1700
Data Index: 1285627 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.3859. Min Act: -0.1700
Data Index: 70638 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.3859. Min Act: -0.1700
Data Index: 5022926 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.3234. Min Act: -0.1700
Data Index: 6354603 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.3546. Min Act: -0.1700
Data Index: 2047020 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.3234. Min Act: -0.1700
Data Index: 965435 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.3234. Min Act: -0.1700
Data Index: 8565060 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3234. Min Range: -7.3234
Max Act: 6.2921. Min Act: -0.1700
Data Index: 1049776 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19