Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.6793. Min Act: -0.1700
Data Index: 5678133 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.4605. Min Act: -0.1700
Data Index: 3869232 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.3980. Min Act: -0.1700
Data Index: 5698827 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.3355. Min Act: -0.1700
Data Index: 1218098 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.3355. Min Act: -0.1700
Data Index: 2428982 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.3355. Min Act: -0.1700
Data Index: 8790530 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2730. Min Act: -0.1700
Data Index: 148432 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2730. Min Act: -0.1700
Data Index: 7363543 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2730. Min Act: -0.1700
Data Index: 2102120 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2418. Min Act: -0.1700
Data Index: 700623 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2418. Min Act: -0.1700
Data Index: 5491733 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2105. Min Act: -0.1700
Data Index: 1595847 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2105. Min Act: -0.1700
Data Index: 4469827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2105. Min Act: -0.1700
Data Index: 6505436 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2105. Min Act: -0.1700
Data Index: 6454313 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.1793. Min Act: -0.1700
Data Index: 739488 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.2105. Min Act: -0.1700
Data Index: 552641 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.1793. Min Act: -0.1700
Data Index: 5442707 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.1793. Min Act: -0.1700
Data Index: 1319725 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6793. Min Range: -4.6793
Max Act: 4.1480. Min Act: -0.1700
Data Index: 4888253 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19