Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1795 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.3105. Min Act: -0.1700
Data Index: 5550211 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.2480. Min Act: -0.1700
Data Index: 6068572 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.1543. Min Act: -0.1700
Data Index: 1308545 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.1230. Min Act: -0.1700
Data Index: 676055 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.1230. Min Act: -0.1700
Data Index: 3522235 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0918. Min Act: -0.1700
Data Index: 2795950 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0918. Min Act: -0.1700
Data Index: 4800466 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.1230. Min Act: -0.1700
Data Index: 2172413 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0605. Min Act: -0.1700
Data Index: 2495589 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0293. Min Act: -0.1700
Data Index: 3451797 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0605. Min Act: -0.1700
Data Index: 4290278 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0293. Min Act: -0.1700
Data Index: 747712 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0293. Min Act: -0.1700
Data Index: 4489510 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0293. Min Act: -0.1700
Data Index: 4776739 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0293. Min Act: -0.1700
Data Index: 1609078 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3105. Min Range: -5.3105
Max Act: 5.0293. Min Act: -0.1700
Data Index: 3411209 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9668. Min Act: -0.1700
Data Index: 2965871 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9668. Min Act: -0.1700
Data Index: 7100832 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 5760231 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3105. Min Range: -5.3105
Max Act: 4.9355. Min Act: -0.1700
Data Index: 5514502 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19