Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3191 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1173. Min Range: -6.1173
Max Act: 6.1173. Min Act: -0.1700
Data Index: 7290344 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1173. Min Range: -6.1173
Max Act: 6.0860. Min Act: -0.1700
Data Index: 4792632 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.9610. Min Act: -0.1700
Data Index: 42870 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.9610. Min Act: -0.1700
Data Index: 3520676 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.9610. Min Act: -0.1700
Data Index: 4349089 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.9610. Min Act: -0.1700
Data Index: 8739209 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.9610. Min Act: -0.1700
Data Index: 1323061 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.9298. Min Act: -0.1700
Data Index: 5998852 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8985. Min Act: -0.1700
Data Index: 7501889 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8985. Min Act: -0.1700
Data Index: 8335080 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8985. Min Act: -0.1700
Data Index: 1363745 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8673. Min Act: -0.1700
Data Index: 5182021 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8673. Min Act: -0.1700
Data Index: 7044583 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8673. Min Act: -0.1700
Data Index: 3230491 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8360. Min Act: -0.1700
Data Index: 2023298 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8360. Min Act: -0.1700
Data Index: 1052615 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8048. Min Act: -0.1700
Data Index: 4476453 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8360. Min Act: -0.1700
Data Index: 2920560 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.7735. Min Act: -0.1700
Data Index: 1896868 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8048. Min Act: -0.1700
Data Index: 412410 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19