Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.7560. Min Act: -0.1700
Data Index: 5236368 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.7560. Min Act: -0.1700
Data Index: 7612112 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.7248. Min Act: -0.1700
Data Index: 6417737 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.6623. Min Act: -0.1700
Data Index: 6323999 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.5373. Min Act: -0.1700
Data Index: 7553677 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.3185. Min Act: -0.1700
Data Index: 8431505 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.3498. Min Act: -0.1700
Data Index: 512694 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.2560. Min Act: -0.1700
Data Index: 3874403 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.2248. Min Act: -0.1700
Data Index: 7951093 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.1935. Min Act: -0.1700
Data Index: 776153 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.1935. Min Act: -0.1700
Data Index: 8635413 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.1935. Min Act: -0.1700
Data Index: 7061673 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.2248. Min Act: -0.1700
Data Index: 8635409 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.1935. Min Act: -0.1700
Data Index: 8635408 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.1623. Min Act: -0.1700
Data Index: 8635399 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.0998. Min Act: -0.1700
Data Index: 8635405 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.1310. Min Act: -0.1700
Data Index: 8635412 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.1623. Min Act: -0.1700
Data Index: 8635417 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.0998. Min Act: -0.1700
Data Index: 3668426 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7560. Min Range: -6.7560
Max Act: 6.1623. Min Act: -0.1700
Data Index: 4357832 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19