Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9166. Min Range: -9.9166
Max Act: 9.9166. Min Act: -0.1700
Data Index: 2611627 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9166. Min Range: -9.9166
Max Act: 9.4791. Min Act: -0.1700
Data Index: 6069967 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9166. Min Range: -9.9166
Max Act: 9.2916. Min Act: -0.1700
Data Index: 1339785 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9166. Min Range: -9.9166
Max Act: 9.1666. Min Act: -0.1700
Data Index: 7680034 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9166. Min Range: -9.9166
Max Act: 9.1666. Min Act: -0.1700
Data Index: 3568874 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9166. Min Range: -9.9166
Max Act: 9.1041. Min Act: -0.1700
Data Index: 1523705 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9166. Min Range: -9.9166
Max Act: 9.0416. Min Act: -0.1700
Data Index: 8715048 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9166. Min Range: -9.9166
Max Act: 9.0416. Min Act: -0.1700
Data Index: 6574356 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.9791. Min Act: -0.1700
Data Index: 1271068 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.9166. Min Act: -0.1700
Data Index: 8331342 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.9791. Min Act: -0.1700
Data Index: 3069184 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.9791. Min Act: -0.1700
Data Index: 2907636 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.9166. Min Act: -0.1700
Data Index: 5259109 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.9166. Min Act: -0.1700
Data Index: 1133295 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.8541. Min Act: -0.1700
Data Index: 4525982 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.8541. Min Act: -0.1700
Data Index: 5954865 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.8541. Min Act: -0.1700
Data Index: 6608808 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.8541. Min Act: -0.1700
Data Index: 3030814 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.8541. Min Act: -0.1700
Data Index: 7046296 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9166. Min Range: -9.9166
Max Act: 8.8541. Min Act: -0.1700
Data Index: 474319 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19