Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2040 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4566. Min Act: -0.1674
Data Index: 2403615 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4478. Min Act: -0.1700
Data Index: 2403617 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4478. Min Act: -0.1700
Data Index: 5969333 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4390. Min Act: -0.1638
Data Index: 2403621 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4214. Min Act: -0.1689
Data Index: 2403620 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4126. Min Act: -0.1700
Data Index: 549108 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4214. Min Act: -0.1700
Data Index: 4226201 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4126. Min Act: -0.1700
Data Index: 3400843 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.4038. Min Act: -0.1700
Data Index: 6687520 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3861. Min Act: -0.1700
Data Index: 7179315 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3861. Min Act: -0.1700
Data Index: 4444708 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3949. Min Act: -0.1700
Data Index: 7904769 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3773. Min Act: -0.1700
Data Index: 425877 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3861. Min Act: -0.1700
Data Index: 6765690 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3685. Min Act: -0.1700
Data Index: 3501758 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3597. Min Act: -0.1700
Data Index: 3677212 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3597. Min Act: -0.1700
Data Index: 2167371 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3597. Min Act: -0.1700
Data Index: 6444793 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3597. Min Act: -0.1700
Data Index: 6441027 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4566. Min Range: -1.4566
Max Act: 1.3597. Min Act: -0.1700
Data Index: 529833 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19