Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.4219. Min Act: -0.1700
Data Index: 7584683 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.3906. Min Act: -0.1700
Data Index: 3114033 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.3281. Min Act: -0.1700
Data Index: 7237493 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.3281. Min Act: -0.1700
Data Index: 1030901 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.2969. Min Act: -0.1700
Data Index: 5604053 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.2656. Min Act: -0.1700
Data Index: 7320234 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.1406. Min Act: -0.1700
Data Index: 7237495 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.1406. Min Act: -0.1700
Data Index: 5679033 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0781. Min Act: -0.1700
Data Index: 577954 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0781. Min Act: -0.1700
Data Index: 8136496 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0781. Min Act: -0.1700
Data Index: 3480831 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0469. Min Act: -0.1700
Data Index: 5109852 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0469. Min Act: -0.1700
Data Index: 1280456 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0469. Min Act: -0.1700
Data Index: 5456507 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0469. Min Act: -0.1700
Data Index: 7837597 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0156. Min Act: -0.1700
Data Index: 4133177 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4219. Min Range: -6.4219
Max Act: 5.9844. Min Act: -0.1700
Data Index: 7569667 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4219. Min Range: -6.4219
Max Act: 6.0156. Min Act: -0.1700
Data Index: 8124213 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4219. Min Range: -6.4219
Max Act: 5.9844. Min Act: -0.1700
Data Index: 7839715 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4219. Min Range: -6.4219
Max Act: 5.9531. Min Act: -0.1700
Data Index: 6491220 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19