Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3848 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.8630. Min Act: -0.1700
Data Index: 3009614 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.8318. Min Act: -0.1700
Data Index: 8539888 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.6130. Min Act: -0.1700
Data Index: 7826024 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.5818. Min Act: -0.1700
Data Index: 5954597 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.5818. Min Act: -0.1700
Data Index: 8330032 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.5193. Min Act: -0.1700
Data Index: 6829666 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.4568. Min Act: -0.1700
Data Index: 7160153 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.4880. Min Act: -0.1700
Data Index: 2830041 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.4568. Min Act: -0.1700
Data Index: 1216194 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.4880. Min Act: -0.1700
Data Index: 6700348 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.4255. Min Act: -0.1700
Data Index: 8448738 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.4568. Min Act: -0.1700
Data Index: 6406005 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.4255. Min Act: -0.1700
Data Index: 8698109 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.3630. Min Act: -0.1700
Data Index: 7005249 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.3318. Min Act: -0.1700
Data Index: 3218110 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.3318. Min Act: -0.1700
Data Index: 718910 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.3318. Min Act: -0.1700
Data Index: 4132726 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.3005. Min Act: -0.1700
Data Index: 4539373 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.3318. Min Act: -0.1700
Data Index: 3036295 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8630. Min Range: -5.8630
Max Act: 5.3005. Min Act: -0.1700
Data Index: 4861718 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19