Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1869 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.8953. Min Act: -0.1700
Data Index: 7584137 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.8794. Min Act: -0.1700
Data Index: 1987965 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.8794. Min Act: -0.1700
Data Index: 7923067 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.8477. Min Act: -0.1700
Data Index: 5203396 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.8477. Min Act: -0.1700
Data Index: 4294170 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.8159. Min Act: -0.1700
Data Index: 7766888 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.8159. Min Act: -0.1700
Data Index: 1593541 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.7681. Min Act: -0.1700
Data Index: 7379656 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.7840. Min Act: -0.1700
Data Index: 3830060 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.7361. Min Act: -0.1700
Data Index: 7205410 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.7042. Min Act: -0.1700
Data Index: 6888371 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.6882. Min Act: -0.1700
Data Index: 644296 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.6721. Min Act: -0.1700
Data Index: 3386677 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.7202. Min Act: -0.1700
Data Index: 8799773 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.6882. Min Act: -0.1700
Data Index: 627092 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.6721. Min Act: -0.1700
Data Index: 3977415 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.6721. Min Act: -0.1700
Data Index: 6574313 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.6721. Min Act: -0.1700
Data Index: 4267763 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.6561. Min Act: -0.1700
Data Index: 3117421 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8953. Min Range: -2.8953
Max Act: 2.6721. Min Act: -0.1700
Data Index: 8115878 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19