Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1156 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.4355. Min Act: -0.1700
Data Index: 5915713 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.4355. Min Act: -0.1700
Data Index: 6925860 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.3418. Min Act: -0.1700
Data Index: 797700 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.2480. Min Act: -0.1700
Data Index: 4599143 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.2168. Min Act: -0.1700
Data Index: 5088933 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.1855. Min Act: -0.1700
Data Index: 4745482 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.1543. Min Act: -0.1700
Data Index: 4534097 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.1230. Min Act: -0.1700
Data Index: 2414778 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.0918. Min Act: -0.1700
Data Index: 2529121 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.0605. Min Act: -0.1700
Data Index: 740063 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.0605. Min Act: -0.1700
Data Index: 4927466 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4355. Min Range: -7.4355
Max Act: 7.0605. Min Act: -0.1700
Data Index: 3796082 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4355. Min Range: -7.4355
Max Act: 6.9980. Min Act: -0.1700
Data Index: 2064711 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4355. Min Range: -7.4355
Max Act: 6.9355. Min Act: -0.1700
Data Index: 6620989 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4355. Min Range: -7.4355
Max Act: 6.9043. Min Act: -0.1700
Data Index: 4737843 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4355. Min Range: -7.4355
Max Act: 6.8730. Min Act: -0.1700
Data Index: 7695991 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4355. Min Range: -7.4355
Max Act: 6.8418. Min Act: -0.1700
Data Index: 1039562 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4355. Min Range: -7.4355
Max Act: 6.8418. Min Act: -0.1700
Data Index: 7565873 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4355. Min Range: -7.4355
Max Act: 6.8418. Min Act: -0.1700
Data Index: 5973486 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4355. Min Range: -7.4355
Max Act: 6.8418. Min Act: -0.1700
Data Index: 4576816 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19