Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3362 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.6351. Min Act: -0.1700
Data Index: 5617211 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.6351. Min Act: -0.1700
Data Index: 6259742 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.6351. Min Act: -0.1700
Data Index: 7051220 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.5726. Min Act: -0.1700
Data Index: 8475962 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.5101. Min Act: -0.1700
Data Index: 2543056 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.3851. Min Act: -0.1700
Data Index: 3717513 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.3851. Min Act: -0.1700
Data Index: 4440731 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.3851. Min Act: -0.1700
Data Index: 8252300 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.3226. Min Act: -0.1700
Data Index: 3879682 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.3226. Min Act: -0.1700
Data Index: 7919380 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.3226. Min Act: -0.1700
Data Index: 4559466 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.3226. Min Act: -0.1700
Data Index: 389532 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.3226. Min Act: -0.1700
Data Index: 210080 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.2601. Min Act: -0.1700
Data Index: 5675819 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.2601. Min Act: -0.1700
Data Index: 4161407 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.1976. Min Act: -0.1700
Data Index: 2390367 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.1976. Min Act: -0.1700
Data Index: 6493720 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.1976. Min Act: -0.1700
Data Index: 5543481 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.1664. Min Act: -0.1700
Data Index: 660131 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6351. Min Range: -8.6351
Max Act: 8.1664. Min Act: -0.1700
Data Index: 6904977 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19