Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4373 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0407. Min Range: -5.0407
Max Act: 5.0407. Min Act: -0.1700
Data Index: 6921283 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0407. Min Range: -5.0407
Max Act: 5.0094. Min Act: -0.1700
Data Index: 3833989 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.9782. Min Act: -0.1700
Data Index: 3301629 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.9469. Min Act: -0.1700
Data Index: 4127326 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.9157. Min Act: -0.1700
Data Index: 6363061 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.8844. Min Act: -0.1700
Data Index: 846350 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.8532. Min Act: -0.1700
Data Index: 2377715 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.8532. Min Act: -0.1700
Data Index: 4846143 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.8219. Min Act: -0.1700
Data Index: 3420796 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.8219. Min Act: -0.1700
Data Index: 3314527 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.8219. Min Act: -0.1700
Data Index: 4905741 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.7907. Min Act: -0.1700
Data Index: 1688324 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.7907. Min Act: -0.1700
Data Index: 8677719 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.7594. Min Act: -0.1700
Data Index: 1083649 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.7594. Min Act: -0.1700
Data Index: 2280346 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.7282. Min Act: -0.1700
Data Index: 1316512 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.7282. Min Act: -0.1700
Data Index: 4609276 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.7282. Min Act: -0.1700
Data Index: 6524585 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.6969. Min Act: -0.1700
Data Index: 7342360 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0407. Min Range: -5.0407
Max Act: 4.7282. Min Act: -0.1700
Data Index: 7711408 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19