Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.9987. Min Act: -0.1700
Data Index: 3458663 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.9987. Min Act: -0.1700
Data Index: 6610659 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.8737. Min Act: -0.1700
Data Index: 1778165 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.9362. Min Act: -0.1700
Data Index: 7799661 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.8112. Min Act: -0.1700
Data Index: 7364990 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.8112. Min Act: -0.1700
Data Index: 2737025 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.7487. Min Act: -0.1700
Data Index: 6304003 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.6862. Min Act: -0.1700
Data Index: 990970 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.7487. Min Act: -0.1700
Data Index: 5627535 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.7487. Min Act: -0.1700
Data Index: 6974027 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.7487. Min Act: -0.1700
Data Index: 6671501 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.6862. Min Act: -0.1700
Data Index: 1647423 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.6862. Min Act: -0.1700
Data Index: 392959 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.6862. Min Act: -0.1700
Data Index: 1030443 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.6237. Min Act: -0.1700
Data Index: 1778181 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.6237. Min Act: -0.1700
Data Index: 8676289 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.6237. Min Act: -0.1700
Data Index: 3678410 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.5612. Min Act: -0.1700
Data Index: 4936879 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.6237. Min Act: -0.1700
Data Index: 1778182 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9987. Min Range: -12.9987
Max Act: 12.5612. Min Act: -0.1700
Data Index: 4156373 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19