Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 301 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.5139. Min Act: -0.1700
Data Index: 1186463 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.4514. Min Act: -0.1700
Data Index: 5370206 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.3264. Min Act: -0.1700
Data Index: 3631263 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.3264. Min Act: -0.1700
Data Index: 1699756 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.3576. Min Act: -0.1700
Data Index: 551326 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1701. Min Act: -0.1700
Data Index: 7002730 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1389. Min Act: -0.1700
Data Index: 3631258 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1389. Min Act: -0.1700
Data Index: 1706709 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1389. Min Act: -0.1700
Data Index: 6819627 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1389. Min Act: -0.1700
Data Index: 4552538 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1076. Min Act: -0.1700
Data Index: 3631260 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1389. Min Act: -0.1700
Data Index: 6629576 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1389. Min Act: -0.1700
Data Index: 8270355 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1076. Min Act: -0.1700
Data Index: 2197436 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.1076. Min Act: -0.1700
Data Index: 5967558 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.0763. Min Act: -0.1700
Data Index: 8036455 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.0451. Min Act: -0.1700
Data Index: 7957677 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.0763. Min Act: -0.1700
Data Index: 1423674 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.0763. Min Act: -0.1700
Data Index: 3896480 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5139. Min Range: -4.5139
Max Act: 4.0451. Min Act: -0.1700
Data Index: 4948997 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19