Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3920 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0282. Min Range: -5.0282
Max Act: 5.0282. Min Act: -0.1700
Data Index: 484957 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.9657. Min Act: -0.1700
Data Index: 5594698 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.9344. Min Act: -0.1700
Data Index: 2469206 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.8094. Min Act: -0.1700
Data Index: 8635757 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.8407. Min Act: -0.1700
Data Index: 3830663 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.7469. Min Act: -0.1700
Data Index: 8140311 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.7469. Min Act: -0.1700
Data Index: 5448790 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.7157. Min Act: -0.1700
Data Index: 6722866 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.7157. Min Act: -0.1700
Data Index: 133855 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6844. Min Act: -0.1700
Data Index: 853033 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6844. Min Act: -0.1700
Data Index: 8459971 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6844. Min Act: -0.1700
Data Index: 8039688 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6532. Min Act: -0.1700
Data Index: 8265341 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6532. Min Act: -0.1700
Data Index: 4915236 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6219. Min Act: -0.1700
Data Index: 5513444 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6532. Min Act: -0.1700
Data Index: 7904232 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6219. Min Act: -0.1700
Data Index: 3197011 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.5907. Min Act: -0.1700
Data Index: 4621287 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.6219. Min Act: -0.1700
Data Index: 7321141 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0282. Min Range: -5.0282
Max Act: 4.5907. Min Act: -0.1700
Data Index: 5721051 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19