Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1006 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.5660. Min Act: -0.1700
Data Index: 5107350 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.5348. Min Act: -0.1700
Data Index: 5930976 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.5035. Min Act: -0.1700
Data Index: 1241397 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.4723. Min Act: -0.1700
Data Index: 8538635 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.3785. Min Act: -0.1700
Data Index: 6873648 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.3785. Min Act: -0.1700
Data Index: 5230931 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.3473. Min Act: -0.1700
Data Index: 1983843 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.3473. Min Act: -0.1700
Data Index: 7946940 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2848. Min Act: -0.1700
Data Index: 4595724 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2535. Min Act: -0.1700
Data Index: 538613 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2535. Min Act: -0.1700
Data Index: 6465188 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2223. Min Act: -0.1700
Data Index: 4237544 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2223. Min Act: -0.1700
Data Index: 687840 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2223. Min Act: -0.1700
Data Index: 3976808 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2223. Min Act: -0.1700
Data Index: 237716 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.1910. Min Act: -0.1700
Data Index: 2513621 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2223. Min Act: -0.1700
Data Index: 7938841 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.2223. Min Act: -0.1700
Data Index: 1966437 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.1910. Min Act: -0.1700
Data Index: 7785074 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5660. Min Range: -5.5660
Max Act: 5.1910. Min Act: -0.1700
Data Index: 491054 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19