Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.8027. Min Act: -0.1700
Data Index: 5807850 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.6777. Min Act: -0.1700
Data Index: 7555523 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.4902. Min Act: -0.1700
Data Index: 8268425 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.4902. Min Act: -0.1700
Data Index: 1437813 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.4902. Min Act: -0.1700
Data Index: 3879615 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.4589. Min Act: -0.1700
Data Index: 3010470 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.4277. Min Act: -0.1700
Data Index: 3563161 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.4277. Min Act: -0.1700
Data Index: 554651 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3964. Min Act: -0.1700
Data Index: 3737481 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3652. Min Act: -0.1700
Data Index: 3336040 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3652. Min Act: -0.1700
Data Index: 7045444 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3339. Min Act: -0.1700
Data Index: 2940181 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3652. Min Act: -0.1700
Data Index: 4330191 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3652. Min Act: -0.1700
Data Index: 3378969 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3339. Min Act: -0.1700
Data Index: 8707078 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3339. Min Act: -0.1700
Data Index: 7195211 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3339. Min Act: -0.1700
Data Index: 2307790 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3339. Min Act: -0.1700
Data Index: 3649899 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3027. Min Act: -0.1700
Data Index: 3148465 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8027. Min Range: -5.8027
Max Act: 5.3027. Min Act: -0.1700
Data Index: 3155440 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19