Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 765 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0226. Min Range: -4.0226
Max Act: 4.0226. Min Act: -0.1700
Data Index: 70048 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.9914. Min Act: -0.1700
Data Index: 975812 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.9914. Min Act: -0.1700
Data Index: 8593857 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.9601. Min Act: -0.1700
Data Index: 3950530 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.9601. Min Act: -0.1700
Data Index: 8487063 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.9288. Min Act: -0.1700
Data Index: 2894 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.9288. Min Act: -0.1700
Data Index: 768537 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.9601. Min Act: -0.1700
Data Index: 8653707 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8976. Min Act: -0.1700
Data Index: 5489610 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8976. Min Act: -0.1700
Data Index: 1717523 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8976. Min Act: -0.1700
Data Index: 2349386 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8976. Min Act: -0.1700
Data Index: 165019 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8976. Min Act: -0.1700
Data Index: 4293511 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8976. Min Act: -0.1700
Data Index: 8179456 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8976. Min Act: -0.1700
Data Index: 7882261 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8663. Min Act: -0.1700
Data Index: 334778 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8663. Min Act: -0.1700
Data Index: 2701842 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8663. Min Act: -0.1700
Data Index: 3096011 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8350. Min Act: -0.1700
Data Index: 5723384 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0226. Min Range: -4.0226
Max Act: 3.8976. Min Act: -0.1700
Data Index: 3585684 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19