Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5066 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.5004. Min Act: -0.1700
Data Index: 4130347 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.3754. Min Act: -0.1700
Data Index: 4695047 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.3754. Min Act: -0.1700
Data Index: 5104840 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.2504. Min Act: -0.1700
Data Index: 933635 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.2504. Min Act: -0.1700
Data Index: 5676041 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.2504. Min Act: -0.1700
Data Index: 5630133 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 1607512 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1879. Min Act: -0.1700
Data Index: 869413 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1879. Min Act: -0.1700
Data Index: 5349592 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1879. Min Act: -0.1700
Data Index: 3337595 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1879. Min Act: -0.1700
Data Index: 7158825 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 5623826 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 4210011 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 5812144 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 420994 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.0629. Min Act: -0.1700
Data Index: 6067831 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 5288338 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 2304159 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 3580185 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5004. Min Range: -8.5004
Max Act: 8.1254. Min Act: -0.1700
Data Index: 5641441 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19