Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 405 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.7273. Min Act: -0.1700
Data Index: 4580992 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.6336. Min Act: -0.1700
Data Index: 4572049 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.6023. Min Act: -0.1700
Data Index: 7143500 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.4773. Min Act: -0.1700
Data Index: 1619127 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.4773. Min Act: -0.1700
Data Index: 1662740 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.4148. Min Act: -0.1700
Data Index: 3788059 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.4148. Min Act: -0.1700
Data Index: 5506097 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.4148. Min Act: -0.1700
Data Index: 4422678 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3836. Min Act: -0.1700
Data Index: 4457775 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3836. Min Act: -0.1700
Data Index: 1194999 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3836. Min Act: -0.1700
Data Index: 5457511 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3523. Min Act: -0.1700
Data Index: 3391927 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3523. Min Act: -0.1700
Data Index: 6816526 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.3211. Min Act: -0.1700
Data Index: 7849059 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2898. Min Act: -0.1700
Data Index: 4403705 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2586. Min Act: -0.1700
Data Index: 3182117 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2898. Min Act: -0.1700
Data Index: 1365076 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2898. Min Act: -0.1700
Data Index: 5405649 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2586. Min Act: -0.1700
Data Index: 5796675 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7273. Min Range: -5.7273
Max Act: 5.2898. Min Act: -0.1700
Data Index: 2854127 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19