Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8319. Min Range: -8.8319
Max Act: 8.8319. Min Act: -0.1700
Data Index: 5868849 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8319. Min Range: -8.8319
Max Act: 8.7069. Min Act: -0.1700
Data Index: 6642959 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8319. Min Range: -8.8319
Max Act: 8.1444. Min Act: -0.1700
Data Index: 6798460 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8319. Min Range: -8.8319
Max Act: 8.0194. Min Act: -0.1700
Data Index: 3446359 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8319. Min Range: -8.8319
Max Act: 8.0819. Min Act: -0.1700
Data Index: 2265598 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8319. Min Range: -8.8319
Max Act: 8.0194. Min Act: -0.1700
Data Index: 3572803 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.9569. Min Act: -0.1700
Data Index: 7970651 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.9569. Min Act: -0.1700
Data Index: 7428708 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.9569. Min Act: -0.1700
Data Index: 1215683 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.8944. Min Act: -0.1700
Data Index: 4362989 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.8944. Min Act: -0.1700
Data Index: 8257092 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.8944. Min Act: -0.1700
Data Index: 8438234 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.8944. Min Act: -0.1700
Data Index: 2125750 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.8319. Min Act: -0.1700
Data Index: 1191548 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.8319. Min Act: -0.1700
Data Index: 2964777 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.8319. Min Act: -0.1700
Data Index: 7534574 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.7069. Min Act: -0.1700
Data Index: 7655471 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.8319. Min Act: -0.1700
Data Index: 3724229 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.7694. Min Act: -0.1700
Data Index: 6375430 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8319. Min Range: -8.8319
Max Act: 7.7694. Min Act: -0.1700
Data Index: 2630371 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19