Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1620 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.4760. Min Act: -0.1700
Data Index: 6463277 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.3510. Min Act: -0.1700
Data Index: 5011529 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.3510. Min Act: -0.1700
Data Index: 3882103 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.3510. Min Act: -0.1700
Data Index: 5651137 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.2260. Min Act: -0.1700
Data Index: 6655085 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.1635. Min Act: -0.1700
Data Index: 2848822 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.1635. Min Act: -0.1700
Data Index: 6769794 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.1635. Min Act: -0.1700
Data Index: 5238224 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.2260. Min Act: -0.1700
Data Index: 1889370 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.1010. Min Act: -0.1700
Data Index: 4184628 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.1010. Min Act: -0.1700
Data Index: 5171547 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.0385. Min Act: -0.1700
Data Index: 2528458 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.0385. Min Act: -0.1700
Data Index: 8764738 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.0385. Min Act: -0.1700
Data Index: 2491721 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.0385. Min Act: -0.1700
Data Index: 6236094 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4760. Min Range: -8.4760
Max Act: 8.0385. Min Act: -0.1700
Data Index: 6590061 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4760. Min Range: -8.4760
Max Act: 7.9760. Min Act: -0.1700
Data Index: 3556350 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4760. Min Range: -8.4760
Max Act: 7.9760. Min Act: -0.1700
Data Index: 930860 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4760. Min Range: -8.4760
Max Act: 7.9760. Min Act: -0.1700
Data Index: 1356193 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4760. Min Range: -8.4760
Max Act: 7.9760. Min Act: -0.1700
Data Index: 8161905 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19