Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.9861. Min Act: -0.1700
Data Index: 2053211 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.9861. Min Act: -0.1700
Data Index: 368275 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.8923. Min Act: -0.1700
Data Index: 99506 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.7986. Min Act: -0.1700
Data Index: 7574663 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.7361. Min Act: -0.1700
Data Index: 1212741 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.7048. Min Act: -0.1700
Data Index: 5502474 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.7048. Min Act: -0.1700
Data Index: 4751838 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.7048. Min Act: -0.1700
Data Index: 3939576 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.6736. Min Act: -0.1700
Data Index: 3286749 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.6736. Min Act: -0.1700
Data Index: 3241135 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.6111. Min Act: -0.1700
Data Index: 8707975 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.6423. Min Act: -0.1700
Data Index: 1836323 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.5798. Min Act: -0.1700
Data Index: 1055255 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.5486. Min Act: -0.1700
Data Index: 7699051 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.5173. Min Act: -0.1700
Data Index: 8615493 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.5173. Min Act: -0.1700
Data Index: 871047 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.4861. Min Act: -0.1700
Data Index: 37214 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.4861. Min Act: -0.1700
Data Index: 3205689 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.4861. Min Act: -0.1700
Data Index: 5006061 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9861. Min Range: -6.9861
Max Act: 6.4861. Min Act: -0.1700
Data Index: 7796294 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19