Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4522 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.3481. Min Act: -0.1700
Data Index: 1574764 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1293. Min Act: -0.1700
Data Index: 1229553 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0668. Min Act: -0.1700
Data Index: 5615614 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9731. Min Act: -0.1700
Data Index: 6857848 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0043. Min Act: -0.1700
Data Index: 173367 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9106. Min Act: -0.1700
Data Index: 4170989 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9106. Min Act: -0.1700
Data Index: 8759388 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9106. Min Act: -0.1700
Data Index: 7501338 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8793. Min Act: -0.1700
Data Index: 6200336 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8793. Min Act: -0.1700
Data Index: 7592641 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 6693811 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8793. Min Act: -0.1700
Data Index: 7880405 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8793. Min Act: -0.1700
Data Index: 8533500 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.9106. Min Act: -0.1700
Data Index: 8105485 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 2983992 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 3110240 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 2323802 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 2219555 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 5399331 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3481. Min Range: -5.3481
Max Act: 4.8481. Min Act: -0.1700
Data Index: 3821899 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19