Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6336. Min Range: -8.6336
Max Act: 8.6336. Min Act: -0.1700
Data Index: 7846542 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6336. Min Range: -8.6336
Max Act: 8.1961. Min Act: -0.1700
Data Index: 6909603 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6336. Min Range: -8.6336
Max Act: 8.1336. Min Act: -0.1700
Data Index: 7417962 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6336. Min Range: -8.6336
Max Act: 8.0086. Min Act: -0.1700
Data Index: 5074231 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6336. Min Range: -8.6336
Max Act: 8.0086. Min Act: -0.1700
Data Index: 3082609 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.9461. Min Act: -0.1700
Data Index: 6832499 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.9461. Min Act: -0.1700
Data Index: 449415 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.7586. Min Act: -0.1700
Data Index: 477320 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6961. Min Act: -0.1700
Data Index: 7206225 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6961. Min Act: -0.1700
Data Index: 1676795 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6961. Min Act: -0.1700
Data Index: 4369118 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.7586. Min Act: -0.1700
Data Index: 6282173 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6336. Min Act: -0.1700
Data Index: 2177144 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6336. Min Act: -0.1700
Data Index: 7985592 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6336. Min Act: -0.1700
Data Index: 7981181 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6336. Min Act: -0.1700
Data Index: 4092180 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6336. Min Act: -0.1700
Data Index: 2629827 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6961. Min Act: -0.1700
Data Index: 7947427 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.6336. Min Act: -0.1700
Data Index: 7194780 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6336. Min Range: -8.6336
Max Act: 7.5711. Min Act: -0.1700
Data Index: 3778658 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19