Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 34 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6826. Min Act: -0.1700
Data Index: 7916387 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6739. Min Act: -0.1700
Data Index: 3561847 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6478. Min Act: -0.1700
Data Index: 1035833 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6478. Min Act: -0.1700
Data Index: 7820301 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6217. Min Act: -0.1699
Data Index: 6498215 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6304. Min Act: -0.1700
Data Index: 6074296 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6217. Min Act: -0.1700
Data Index: 4400240 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6042. Min Act: -0.1700
Data Index: 7820299 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6042. Min Act: -0.1700
Data Index: 6524850 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6042. Min Act: -0.1700
Data Index: 8479414 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6130. Min Act: -0.1700
Data Index: 22768 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6042. Min Act: -0.1700
Data Index: 1627325 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.5955. Min Act: -0.1700
Data Index: 7916381 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.6042. Min Act: -0.1700
Data Index: 93417 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.5955. Min Act: -0.1700
Data Index: 128689 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.5780. Min Act: -0.1700
Data Index: 3962424 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.5868. Min Act: -0.1700
Data Index: 1097743 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.5780. Min Act: -0.1700
Data Index: 8770018 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.5693. Min Act: -0.1700
Data Index: 6971482 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6826. Min Range: -1.6826
Max Act: 1.5605. Min Act: -0.1700
Data Index: 817419 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19