Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.9177. Min Act: -0.1700
Data Index: 2244094 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8864. Min Act: -0.1700
Data Index: 2728129 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8864. Min Act: -0.1700
Data Index: 5414362 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8552. Min Act: -0.1700
Data Index: 2215293 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.9177. Min Act: -0.1700
Data Index: 2080830 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8864. Min Act: -0.1700
Data Index: 1974773 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8864. Min Act: -0.1700
Data Index: 66022 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8552. Min Act: -0.1700
Data Index: 6059605 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8552. Min Act: -0.1700
Data Index: 8513511 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8552. Min Act: -0.1700
Data Index: 1890689 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8239. Min Act: -0.1700
Data Index: 5544714 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8552. Min Act: -0.1700
Data Index: 5703351 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8552. Min Act: -0.1700
Data Index: 5735377 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8239. Min Act: -0.1700
Data Index: 4531493 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8239. Min Act: -0.1700
Data Index: 1228613 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8239. Min Act: -0.1700
Data Index: 118197 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8239. Min Act: -0.1700
Data Index: 1283965 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8239. Min Act: -0.1700
Data Index: 5449351 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8239. Min Act: -0.1700
Data Index: 1377276 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9177. Min Range: -4.9177
Max Act: 4.8552. Min Act: -0.1700
Data Index: 5664698 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19