Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5010 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0243. Min Range: -8.0243
Max Act: 8.0243. Min Act: -0.1700
Data Index: 2496479 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.9618. Min Act: -0.1700
Data Index: 1799719 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.9618. Min Act: -0.1700
Data Index: 5584054 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.6181. Min Act: -0.1700
Data Index: 4154523 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.5868. Min Act: -0.1700
Data Index: 3024552 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.5868. Min Act: -0.1700
Data Index: 2385556 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.4931. Min Act: -0.1700
Data Index: 5116449 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.4306. Min Act: -0.1700
Data Index: 6255357 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.4306. Min Act: -0.1700
Data Index: 5989050 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.4306. Min Act: -0.1700
Data Index: 4961095 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.3993. Min Act: -0.1700
Data Index: 2272733 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.3681. Min Act: -0.1700
Data Index: 4716307 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.3681. Min Act: -0.1700
Data Index: 3986624 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.3681. Min Act: -0.1700
Data Index: 5903167 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.3056. Min Act: -0.1700
Data Index: 5318291 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.2743. Min Act: -0.1700
Data Index: 1063059 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.2743. Min Act: -0.1700
Data Index: 8104855 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.3056. Min Act: -0.1700
Data Index: 5520259 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.2431. Min Act: -0.1700
Data Index: 5988966 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0243. Min Range: -8.0243
Max Act: 7.2431. Min Act: -0.1700
Data Index: 4659231 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19