Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3624 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4560. Min Range: -6.4560
Max Act: 6.4560. Min Act: -0.1700
Data Index: 8147203 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4560. Min Range: -6.4560
Max Act: 6.2685. Min Act: -0.1700
Data Index: 8817984 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4560. Min Range: -6.4560
Max Act: 6.2373. Min Act: -0.1700
Data Index: 1573624 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4560. Min Range: -6.4560
Max Act: 6.2060. Min Act: -0.1700
Data Index: 8711812 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4560. Min Range: -6.4560
Max Act: 6.1435. Min Act: -0.1700
Data Index: 742587 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4560. Min Range: -6.4560
Max Act: 6.0185. Min Act: -0.1700
Data Index: 4038605 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4560. Min Range: -6.4560
Max Act: 6.0185. Min Act: -0.1700
Data Index: 3580375 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.9248. Min Act: -0.1700
Data Index: 2281555 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8935. Min Act: -0.1700
Data Index: 7573354 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8623. Min Act: -0.1700
Data Index: 1045749 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8935. Min Act: -0.1700
Data Index: 1187161 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8935. Min Act: -0.1700
Data Index: 2478914 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8623. Min Act: -0.1700
Data Index: 5550973 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8623. Min Act: -0.1700
Data Index: 5781641 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8623. Min Act: -0.1700
Data Index: 1950314 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.7998. Min Act: -0.1700
Data Index: 2548028 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8310. Min Act: -0.1700
Data Index: 2895389 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8310. Min Act: -0.1700
Data Index: 2680954 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.8310. Min Act: -0.1700
Data Index: 1043507 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4560. Min Range: -6.4560
Max Act: 5.7998. Min Act: -0.1700
Data Index: 3968018 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19