Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3605 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.5088. Min Act: -0.1700
Data Index: 8405671 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.1338. Min Act: -0.1700
Data Index: 868789 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.1338. Min Act: -0.1700
Data Index: 213308 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.1338. Min Act: -0.1700
Data Index: 4889293 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.0713. Min Act: -0.1700
Data Index: 868779 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.0713. Min Act: -0.1700
Data Index: 1998761 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.0088. Min Act: -0.1700
Data Index: 4301957 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.0088. Min Act: -0.1700
Data Index: 6252027 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.0088. Min Act: -0.1700
Data Index: 1998766 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.0088. Min Act: -0.1700
Data Index: 868785 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5088. Min Range: -8.5088
Max Act: 8.0088. Min Act: -0.1700
Data Index: 1998768 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.9463. Min Act: -0.1700
Data Index: 4079464 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.9463. Min Act: -0.1700
Data Index: 2272375 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.9463. Min Act: -0.1700
Data Index: 2316372 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.9463. Min Act: -0.1700
Data Index: 1655247 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.9463. Min Act: -0.1700
Data Index: 6624371 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.8838. Min Act: -0.1700
Data Index: 327128 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.8838. Min Act: -0.1700
Data Index: 5219936 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.8838. Min Act: -0.1700
Data Index: 1998764 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5088. Min Range: -8.5088
Max Act: 7.8838. Min Act: -0.1700
Data Index: 6245720 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19