Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3623 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.8550. Min Act: -0.1700
Data Index: 6769623 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.6050. Min Act: -0.1700
Data Index: 6847612 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.4175. Min Act: -0.1700
Data Index: 5632591 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.4175. Min Act: -0.1700
Data Index: 1483488 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.4800. Min Act: -0.1700
Data Index: 2888940 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.2925. Min Act: -0.1700
Data Index: 3890980 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.2925. Min Act: -0.1700
Data Index: 971144 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.1675. Min Act: -0.1700
Data Index: 3477573 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.1050. Min Act: -0.1700
Data Index: 6357455 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.1050. Min Act: -0.1700
Data Index: 6541392 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.0425. Min Act: -0.1700
Data Index: 2471288 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8550. Min Range: -9.8550
Max Act: 9.0425. Min Act: -0.1700
Data Index: 3404990 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8550. Min Range: -9.8550
Max Act: 8.9800. Min Act: -0.1700
Data Index: 368431 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8550. Min Range: -9.8550
Max Act: 8.9800. Min Act: -0.1700
Data Index: 6352037 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8550. Min Range: -9.8550
Max Act: 8.9175. Min Act: -0.1700
Data Index: 4657814 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8550. Min Range: -9.8550
Max Act: 8.9175. Min Act: -0.1700
Data Index: 1752012 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8550. Min Range: -9.8550
Max Act: 8.9175. Min Act: -0.1700
Data Index: 4626327 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8550. Min Range: -9.8550
Max Act: 8.9175. Min Act: -0.1700
Data Index: 2294853 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8550. Min Range: -9.8550
Max Act: 8.8550. Min Act: -0.1700
Data Index: 4822564 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8550. Min Range: -9.8550
Max Act: 8.8550. Min Act: -0.1700
Data Index: 2233610 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19