Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3059 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1731. Min Range: -5.1731
Max Act: 5.1731. Min Act: -0.1700
Data Index: 6744572 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1731. Min Range: -5.1731
Max Act: 5.1418. Min Act: -0.1700
Data Index: 5517988 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1731. Min Range: -5.1731
Max Act: 5.1106. Min Act: -0.1700
Data Index: 6502185 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1731. Min Range: -5.1731
Max Act: 5.0168. Min Act: -0.1700
Data Index: 1082476 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.9856. Min Act: -0.1700
Data Index: 4463211 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.9543. Min Act: -0.1700
Data Index: 7167246 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8918. Min Act: -0.1700
Data Index: 2826903 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.9231. Min Act: -0.1700
Data Index: 2539805 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.9543. Min Act: -0.1700
Data Index: 914230 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8918. Min Act: -0.1700
Data Index: 4761615 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8918. Min Act: -0.1700
Data Index: 5174334 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8918. Min Act: -0.1700
Data Index: 5297198 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8918. Min Act: -0.1700
Data Index: 473713 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8918. Min Act: -0.1700
Data Index: 5174335 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8606. Min Act: -0.1700
Data Index: 5710968 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8293. Min Act: -0.1700
Data Index: 448285 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8293. Min Act: -0.1700
Data Index: 299896 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.7981. Min Act: -0.1700
Data Index: 5303599 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.8606. Min Act: -0.1700
Data Index: 8184581 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1731. Min Range: -5.1731
Max Act: 4.7981. Min Act: -0.1700
Data Index: 1985275 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19