Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2190 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.9478. Min Act: -0.1700
Data Index: 3673482 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.8853. Min Act: -0.1700
Data Index: 623093 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.8853. Min Act: -0.1700
Data Index: 5644027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.8540. Min Act: -0.1700
Data Index: 3007979 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.7603. Min Act: -0.1700
Data Index: 8428496 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.7603. Min Act: -0.1700
Data Index: 1025927 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6978. Min Act: -0.1700
Data Index: 3909994 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6978. Min Act: -0.1700
Data Index: 2017431 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6978. Min Act: -0.1700
Data Index: 4793498 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6665. Min Act: -0.1700
Data Index: 7729768 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6353. Min Act: -0.1700
Data Index: 4048408 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6353. Min Act: -0.1700
Data Index: 3089248 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6353. Min Act: -0.1700
Data Index: 3608571 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6040. Min Act: -0.1700
Data Index: 4916564 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6040. Min Act: -0.1700
Data Index: 3713655 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.6040. Min Act: -0.1700
Data Index: 3334718 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.5728. Min Act: -0.1700
Data Index: 1372581 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.5415. Min Act: -0.1700
Data Index: 4532530 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.5415. Min Act: -0.1700
Data Index: 8769358 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9478. Min Range: -4.9478
Max Act: 4.5103. Min Act: -0.1700
Data Index: 2986205 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19