Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1121. Min Range: -5.1121
Max Act: 5.1121. Min Act: -0.1700
Data Index: 4322837 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1121. Min Range: -5.1121
Max Act: 5.0496. Min Act: -0.1700
Data Index: 6653056 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.9559. Min Act: -0.1700
Data Index: 1057396 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.8934. Min Act: -0.1700
Data Index: 7319180 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.8621. Min Act: -0.1700
Data Index: 6581512 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.7684. Min Act: -0.1700
Data Index: 271085 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.7684. Min Act: -0.1700
Data Index: 7924052 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.7059. Min Act: -0.1700
Data Index: 4935160 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6746. Min Act: -0.1700
Data Index: 7567657 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.7059. Min Act: -0.1700
Data Index: 7345144 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6746. Min Act: -0.1700
Data Index: 190361 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6746. Min Act: -0.1700
Data Index: 3978567 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6746. Min Act: -0.1700
Data Index: 1322987 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6434. Min Act: -0.1700
Data Index: 7556021 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6434. Min Act: -0.1700
Data Index: 5032970 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6434. Min Act: -0.1700
Data Index: 968608 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6121. Min Act: -0.1700
Data Index: 5115625 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6121. Min Act: -0.1700
Data Index: 6345982 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6434. Min Act: -0.1700
Data Index: 532561 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1121. Min Range: -5.1121
Max Act: 4.6121. Min Act: -0.1700
Data Index: 5720499 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19