Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3442 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1496. Min Range: -7.1496
Max Act: 7.1496. Min Act: -0.1700
Data Index: 6563965 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1496. Min Range: -7.1496
Max Act: 7.1184. Min Act: -0.1700
Data Index: 729176 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1496. Min Range: -7.1496
Max Act: 7.1184. Min Act: -0.1700
Data Index: 7874139 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1496. Min Range: -7.1496
Max Act: 7.0246. Min Act: -0.1700
Data Index: 7539764 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.9309. Min Act: -0.1700
Data Index: 880438 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.8684. Min Act: -0.1700
Data Index: 3681485 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.8371. Min Act: -0.1700
Data Index: 490883 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.8059. Min Act: -0.1700
Data Index: 7248137 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.8059. Min Act: -0.1700
Data Index: 2144427 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.7434. Min Act: -0.1700
Data Index: 6186790 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.6496. Min Act: -0.1700
Data Index: 5075274 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.6496. Min Act: -0.1700
Data Index: 7328758 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.6184. Min Act: -0.1700
Data Index: 4519340 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.6184. Min Act: -0.1700
Data Index: 6157507 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.5246. Min Act: -0.1700
Data Index: 8548620 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.5246. Min Act: -0.1700
Data Index: 1691671 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.4934. Min Act: -0.1700
Data Index: 7046540 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.4934. Min Act: -0.1700
Data Index: 1012834 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.4934. Min Act: -0.1700
Data Index: 988794 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1496. Min Range: -7.1496
Max Act: 6.5246. Min Act: -0.1700
Data Index: 268056 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19