Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.3883. Min Act: -0.1700
Data Index: 5760400 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.3258. Min Act: -0.1700
Data Index: 31565 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.2633. Min Act: -0.1700
Data Index: 3558439 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.2946. Min Act: -0.1700
Data Index: 2853831 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.2008. Min Act: -0.1700
Data Index: 3010672 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.1696. Min Act: -0.1700
Data Index: 457589 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.1071. Min Act: -0.1700
Data Index: 2498096 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.0758. Min Act: -0.1700
Data Index: 8054242 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.0133. Min Act: -0.1700
Data Index: 457587 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.9508. Min Act: -0.1700
Data Index: 8652977 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.9508. Min Act: -0.1700
Data Index: 4718934 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.9196. Min Act: -0.1700
Data Index: 6540218 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.9196. Min Act: -0.1700
Data Index: 4815308 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.9508. Min Act: -0.1700
Data Index: 3216083 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.9196. Min Act: -0.1700
Data Index: 3588164 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.8883. Min Act: -0.1700
Data Index: 1303270 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.9196. Min Act: -0.1700
Data Index: 5443986 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.8883. Min Act: -0.1700
Data Index: 5294225 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.8883. Min Act: -0.1700
Data Index: 4798126 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.8571. Min Act: -0.1700
Data Index: 1060902 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19