Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1415 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.9108. Min Act: -0.1700
Data Index: 8060161 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.8170. Min Act: -0.1700
Data Index: 3539522 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.7232. Min Act: -0.1700
Data Index: 7986918 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.6293. Min Act: -0.1700
Data Index: 643599 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.6293. Min Act: -0.1700
Data Index: 643598 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.6293. Min Act: -0.1700
Data Index: 4065899 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.6293. Min Act: -0.1700
Data Index: 3997975 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.6293. Min Act: -0.1700
Data Index: 1650713 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.6293. Min Act: -0.1700
Data Index: 6884647 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5980. Min Act: -0.1700
Data Index: 4684963 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5980. Min Act: -0.1700
Data Index: 2768468 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5980. Min Act: -0.1700
Data Index: 5332962 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5980. Min Act: -0.1700
Data Index: 3612928 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5980. Min Act: -0.1700
Data Index: 1372776 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5667. Min Act: -0.1700
Data Index: 2098235 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5667. Min Act: -0.1700
Data Index: 6896714 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5354. Min Act: -0.1700
Data Index: 6603586 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5667. Min Act: -0.1700
Data Index: 8224437 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5667. Min Act: -0.1700
Data Index: 5185162 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9108. Min Range: -3.9108
Max Act: 3.5667. Min Act: -0.1700
Data Index: 7206951 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19