Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3808 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.9631. Min Act: -0.1700
Data Index: 474732 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.9376. Min Act: -0.1700
Data Index: 8543305 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.9376. Min Act: -0.1699
Data Index: 2275776 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.9121. Min Act: -0.1700
Data Index: 1700632 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.9206. Min Act: -0.1700
Data Index: 8738605 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.9206. Min Act: -0.1700
Data Index: 1937110 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8950. Min Act: -0.1700
Data Index: 8169834 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.9036. Min Act: -0.1700
Data Index: 3218184 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8865. Min Act: -0.1700
Data Index: 4180144 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8780. Min Act: -0.1700
Data Index: 5565109 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8780. Min Act: -0.1700
Data Index: 887575 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8780. Min Act: -0.1700
Data Index: 4235291 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8780. Min Act: -0.1700
Data Index: 2657421 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8609. Min Act: -0.1700
Data Index: 826358 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8780. Min Act: -0.1700
Data Index: 2449009 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8780. Min Act: -0.1687
Data Index: 6280204 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8694. Min Act: -0.1700
Data Index: 655114 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8523. Min Act: -0.1700
Data Index: 4155388 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8609. Min Act: -0.1700
Data Index: 2231208 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9631. Min Range: -1.9631
Max Act: 1.8609. Min Act: -0.1700
Data Index: 7802851 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19