Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3839 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9882. Min Range: -8.9882
Max Act: 8.9882. Min Act: -0.1700
Data Index: 2252387 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.9882. Min Act: -0.1700
Data Index: 6057722 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.5507. Min Act: -0.1700
Data Index: 3348470 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.4882. Min Act: -0.1700
Data Index: 7483473 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.3632. Min Act: -0.1700
Data Index: 1228345 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.0820. Min Act: -0.1700
Data Index: 6159226 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2695. Min Act: -0.1700
Data Index: 5938177 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.3632. Min Act: -0.1700
Data Index: 6303877 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.3320. Min Act: -0.1700
Data Index: 2069570 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2695. Min Act: -0.1700
Data Index: 6430152 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2695. Min Act: -0.1700
Data Index: 7774939 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2695. Min Act: -0.1700
Data Index: 5694968 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2695. Min Act: -0.1700
Data Index: 5767991 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2382. Min Act: -0.1700
Data Index: 6549397 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2382. Min Act: -0.1700
Data Index: 1537556 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2382. Min Act: -0.1700
Data Index: 5806076 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2382. Min Act: -0.1700
Data Index: 102376 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2695. Min Act: -0.1700
Data Index: 8182794 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.2695. Min Act: -0.1700
Data Index: 2178531 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9882. Min Range: -8.9882
Max Act: 7.1757. Min Act: -0.1700
Data Index: 134466 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19