Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1334 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.7319. Min Act: -0.1256
Data Index: 4202886 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6712. Min Act: 0.0035
Data Index: 2869263 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6625. Min Act: 0.0804
Data Index: 1587757 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6538. Min Act: -0.1055
Data Index: 6174487 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6364. Min Act: -0.0654
Data Index: 2504316 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6364. Min Act: -0.1270
Data Index: 4032963 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: -0.0647
Data Index: 7466551 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: -0.0936
Data Index: 8137254 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6277. Min Act: -0.0216
Data Index: 189797 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: -0.1252
Data Index: 916979 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: -0.0735
Data Index: 3582740 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: -0.0798
Data Index: 2041838 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: -0.0442
Data Index: 3677620 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: -0.1434
Data Index: 4963325 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6102. Min Act: -0.0720
Data Index: 2516963 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: 0.0148
Data Index: 1587763 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6102. Min Act: -0.0891
Data Index: 2826983 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6102. Min Act: -0.1618
Data Index: 4348569 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6102. Min Act: -0.1420
Data Index: 8224234 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7319. Min Range: -1.7319
Max Act: 1.6190. Min Act: -0.0503
Data Index: 3708842 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19