Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3365 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.6109. Min Act: -0.1700
Data Index: 6431252 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.6422. Min Act: -0.1700
Data Index: 6247965 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.4234. Min Act: -0.1700
Data Index: 4446202 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.3609. Min Act: -0.1700
Data Index: 6580712 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.3297. Min Act: -0.1700
Data Index: 2102671 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.3297. Min Act: -0.1700
Data Index: 1440737 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.3297. Min Act: -0.1700
Data Index: 3605398 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.3297. Min Act: -0.1700
Data Index: 1468184 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.2359. Min Act: -0.1700
Data Index: 1548974 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.2359. Min Act: -0.1700
Data Index: 4501698 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.2047. Min Act: -0.1700
Data Index: 1733270 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.2047. Min Act: -0.1700
Data Index: 4236271 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.1109. Min Act: -0.1700
Data Index: 3323401 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.0172. Min Act: -0.1700
Data Index: 3440951 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.0484. Min Act: -0.1700
Data Index: 7825840 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.0484. Min Act: -0.1700
Data Index: 1647562 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.0484. Min Act: -0.1700
Data Index: 129639 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.0172. Min Act: -0.1700
Data Index: 1135484 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.0172. Min Act: -0.1700
Data Index: 3176513 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6422. Min Range: -7.6422
Max Act: 7.0172. Min Act: -0.1700
Data Index: 1355788 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19