Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.5094. Min Act: -0.1700
Data Index: 708720 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.4156. Min Act: -0.1700
Data Index: 5286549 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.3844. Min Act: -0.1700
Data Index: 4787418 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.3219. Min Act: -0.1700
Data Index: 4244312 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.2906. Min Act: -0.1700
Data Index: 601423 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.2281. Min Act: -0.1700
Data Index: 3219875 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.1656. Min Act: -0.1700
Data Index: 99823 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.1344. Min Act: -0.1700
Data Index: 6858193 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.1031. Min Act: -0.1700
Data Index: 6807120 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.1031. Min Act: -0.1700
Data Index: 5689497 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.1344. Min Act: -0.1700
Data Index: 7152587 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.1344. Min Act: -0.1700
Data Index: 5096595 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.1031. Min Act: -0.1700
Data Index: 1318467 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.0719. Min Act: -0.1700
Data Index: 2240528 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.1031. Min Act: -0.1700
Data Index: 3090379 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.0719. Min Act: -0.1700
Data Index: 3994305 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.0719. Min Act: -0.1700
Data Index: 3479734 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.0719. Min Act: -0.1700
Data Index: 2277442 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.0406. Min Act: -0.1700
Data Index: 1347147 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5094. Min Range: -7.5094
Max Act: 7.0406. Min Act: -0.1700
Data Index: 977086 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19