Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.6306. Min Act: -0.1700
Data Index: 2591388 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.5056. Min Act: -0.1700
Data Index: 3409373 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.3181. Min Act: -0.1700
Data Index: 1596171 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.2556. Min Act: -0.1700
Data Index: 7628002 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.2556. Min Act: -0.1700
Data Index: 4960863 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.1931. Min Act: -0.1700
Data Index: 2921428 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.0681. Min Act: -0.1700
Data Index: 8088042 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.1306. Min Act: -0.1700
Data Index: 658162 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.1306. Min Act: -0.1700
Data Index: 8827814 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.1306. Min Act: -0.1700
Data Index: 4661900 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.1306. Min Act: -0.1700
Data Index: 3099911 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.1306. Min Act: -0.1700
Data Index: 6354239 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.0681. Min Act: -0.1700
Data Index: 865770 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.0681. Min Act: -0.1700
Data Index: 5965324 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.0056. Min Act: -0.1700
Data Index: 5855284 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.0056. Min Act: -0.1700
Data Index: 8385214 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6306. Min Range: -8.6306
Max Act: 7.9431. Min Act: -0.1700
Data Index: 1269914 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6306. Min Range: -8.6306
Max Act: 8.0056. Min Act: -0.1700
Data Index: 8216567 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6306. Min Range: -8.6306
Max Act: 7.9431. Min Act: -0.1700
Data Index: 6769136 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6306. Min Range: -8.6306
Max Act: 7.8806. Min Act: -0.1700
Data Index: 2797434 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19