Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6610. Min Range: -12.6610
Max Act: 12.6610. Min Act: -0.1700
Data Index: 2476909 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6610. Min Range: -12.6610
Max Act: 12.4735. Min Act: -0.1700
Data Index: 100210 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6610. Min Range: -12.6610
Max Act: 12.4110. Min Act: -0.1700
Data Index: 1502209 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6610. Min Range: -12.6610
Max Act: 12.0985. Min Act: -0.1700
Data Index: 7722387 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6610. Min Range: -12.6610
Max Act: 12.0985. Min Act: -0.1700
Data Index: 4944724 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6610. Min Range: -12.6610
Max Act: 12.0360. Min Act: -0.1700
Data Index: 7786337 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6610. Min Range: -12.6610
Max Act: 12.0360. Min Act: -0.1700
Data Index: 8762461 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.9735. Min Act: -0.1700
Data Index: 7586593 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6610. Min Range: -12.6610
Max Act: 12.0360. Min Act: -0.1700
Data Index: 197982 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.8485. Min Act: -0.1700
Data Index: 7532553 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.8485. Min Act: -0.1700
Data Index: 6509623 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.7860. Min Act: -0.1700
Data Index: 8195051 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.7860. Min Act: -0.1700
Data Index: 701510 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.7860. Min Act: -0.1700
Data Index: 4602531 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.8485. Min Act: -0.1700
Data Index: 8572044 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.7860. Min Act: -0.1700
Data Index: 1515720 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.7860. Min Act: -0.1700
Data Index: 5038921 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.8485. Min Act: -0.1700
Data Index: 4583240 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.7235. Min Act: -0.1700
Data Index: 5537165 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6610. Min Range: -12.6610
Max Act: 11.7235. Min Act: -0.1700
Data Index: 2719747 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19