Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 968 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5973. Min Act: -0.1700
Data Index: 1747424 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5812. Min Act: -0.1700
Data Index: 3115167 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5651. Min Act: -0.1700
Data Index: 1310093 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5651. Min Act: -0.1700
Data Index: 6422603 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5812. Min Act: -0.1700
Data Index: 2002950 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5651. Min Act: -0.1700
Data Index: 3624624 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5490. Min Act: -0.1700
Data Index: 6776723 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5328. Min Act: -0.1700
Data Index: 2769167 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5328. Min Act: -0.1700
Data Index: 6422604 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5005. Min Act: -0.1700
Data Index: 2701321 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.4842. Min Act: -0.1700
Data Index: 7626913 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5005. Min Act: -0.1700
Data Index: 1761403 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5005. Min Act: -0.1700
Data Index: 2701318 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.4842. Min Act: -0.1700
Data Index: 4928545 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.5005. Min Act: -0.1700
Data Index: 2701322 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.4842. Min Act: -0.1700
Data Index: 8446914 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.4842. Min Act: -0.1700
Data Index: 8183176 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.4680. Min Act: -0.1700
Data Index: 4721216 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.4518. Min Act: -0.1700
Data Index: 62894 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5973. Min Range: -2.5973
Max Act: 2.4680. Min Act: -0.1700
Data Index: 3310016 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19