Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4108 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0677. Min Range: -9.0677
Max Act: 9.0677. Min Act: -0.1700
Data Index: 4636761 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.9427. Min Act: -0.1700
Data Index: 4339916 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.8177. Min Act: -0.1700
Data Index: 7826227 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.6927. Min Act: -0.1700
Data Index: 7601951 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.6302. Min Act: -0.1700
Data Index: 7299931 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.6302. Min Act: -0.1700
Data Index: 5804234 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.5677. Min Act: -0.1700
Data Index: 2055691 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.5052. Min Act: -0.1700
Data Index: 1750035 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.5052. Min Act: -0.1700
Data Index: 1965456 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.5052. Min Act: -0.1700
Data Index: 1549617 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.5052. Min Act: -0.1700
Data Index: 4707028 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.4427. Min Act: -0.1700
Data Index: 3753336 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.4427. Min Act: -0.1700
Data Index: 6192722 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.3802. Min Act: -0.1700
Data Index: 1846432 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.3802. Min Act: -0.1700
Data Index: 4260909 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.3802. Min Act: -0.1700
Data Index: 3508616 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.3177. Min Act: -0.1700
Data Index: 5490194 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.3177. Min Act: -0.1700
Data Index: 3186220 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.3177. Min Act: -0.1700
Data Index: 4355305 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0677. Min Range: -9.0677
Max Act: 8.3177. Min Act: -0.1700
Data Index: 5858109 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19