Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.9286. Min Act: -0.1700
Data Index: 5634377 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.8974. Min Act: -0.1700
Data Index: 5648493 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.8661. Min Act: -0.1700
Data Index: 5470953 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.8349. Min Act: -0.1700
Data Index: 3738334 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.8036. Min Act: -0.1700
Data Index: 4721290 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.8036. Min Act: -0.1700
Data Index: 6067844 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.8036. Min Act: -0.1700
Data Index: 5726203 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.7724. Min Act: -0.1700
Data Index: 2085471 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.7099. Min Act: -0.1700
Data Index: 880811 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.7099. Min Act: -0.1700
Data Index: 4648888 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.7099. Min Act: -0.1700
Data Index: 3003580 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.7411. Min Act: -0.1700
Data Index: 629390 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.7099. Min Act: -0.1700
Data Index: 767642 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.6786. Min Act: -0.1700
Data Index: 4110263 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.6786. Min Act: -0.1700
Data Index: 4308770 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.6474. Min Act: -0.1700
Data Index: 3539276 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.6474. Min Act: -0.1700
Data Index: 7356296 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.6161. Min Act: -0.1700
Data Index: 315621 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.6161. Min Act: -0.1700
Data Index: 1231315 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9286. Min Range: -4.9286
Max Act: 4.6161. Min Act: -0.1700
Data Index: 5032826 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19