Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.6683. Min Act: -0.1700
Data Index: 6923548 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.5433. Min Act: -0.1700
Data Index: 8448789 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.3870. Min Act: -0.1700
Data Index: 7833516 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.1370. Min Act: -0.1700
Data Index: 308603 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.1683. Min Act: -0.1700
Data Index: 3947372 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.1370. Min Act: -0.1700
Data Index: 3368500 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.1058. Min Act: -0.1700
Data Index: 2156579 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.0745. Min Act: -0.1700
Data Index: 1231813 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.0745. Min Act: -0.1700
Data Index: 6281530 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.0120. Min Act: -0.1700
Data Index: 8616146 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6683. Min Range: -6.6683
Max Act: 6.0120. Min Act: -0.1700
Data Index: 5637221 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.9808. Min Act: -0.1700
Data Index: 5282247 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.9808. Min Act: -0.1700
Data Index: 2303687 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.9808. Min Act: -0.1700
Data Index: 3983369 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.9495. Min Act: -0.1700
Data Index: 7964819 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.9495. Min Act: -0.1700
Data Index: 7380498 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.9495. Min Act: -0.1700
Data Index: 4001326 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.9183. Min Act: -0.1700
Data Index: 1013582 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.8870. Min Act: -0.1700
Data Index: 3394553 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6683. Min Range: -6.6683
Max Act: 5.8870. Min Act: -0.1700
Data Index: 166206 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19