Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0291. Min Range: -6.0291
Max Act: 6.0291. Min Act: -0.1700
Data Index: 5046338 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0291. Min Range: -6.0291
Max Act: 6.0291. Min Act: -0.1700
Data Index: 1554359 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.9354. Min Act: -0.1700
Data Index: 2217012 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.9041. Min Act: -0.1700
Data Index: 4678945 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.9354. Min Act: -0.1700
Data Index: 538337 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.8729. Min Act: -0.1700
Data Index: 3100098 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.8104. Min Act: -0.1700
Data Index: 4914897 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.8104. Min Act: -0.1700
Data Index: 5888287 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.8104. Min Act: -0.1700
Data Index: 4101215 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.8104. Min Act: -0.1700
Data Index: 2299952 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4766178 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7479. Min Act: -0.1700
Data Index: 6189902 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4394292 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7791. Min Act: -0.1700
Data Index: 2279964 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7791. Min Act: -0.1700
Data Index: 7814525 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4303953 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7791. Min Act: -0.1700
Data Index: 2215623 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7166. Min Act: -0.1700
Data Index: 7635685 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7479. Min Act: -0.1700
Data Index: 776866 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0291. Min Range: -6.0291
Max Act: 5.7479. Min Act: -0.1700
Data Index: 1711181 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19