Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 922 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.8009. Min Act: -0.1700
Data Index: 4411618 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3608901 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.7384. Min Act: -0.1700
Data Index: 3923679 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.7697. Min Act: -0.1700
Data Index: 492507 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.7072. Min Act: -0.1700
Data Index: 2339910 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6759. Min Act: -0.1700
Data Index: 4336731 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6759. Min Act: -0.1700
Data Index: 1955631 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6759. Min Act: -0.1700
Data Index: 2317414 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6447. Min Act: -0.1700
Data Index: 2164084 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6447. Min Act: -0.1700
Data Index: 6746292 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6134. Min Act: -0.1700
Data Index: 581474 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6134. Min Act: -0.1700
Data Index: 16305 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6134. Min Act: -0.1700
Data Index: 288619 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5822. Min Act: -0.1700
Data Index: 6372656 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5822. Min Act: -0.1700
Data Index: 3934634 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.6134. Min Act: -0.1700
Data Index: 8016563 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5197. Min Act: -0.1700
Data Index: 5967825 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5509. Min Act: -0.1700
Data Index: 7096591 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.5509. Min Act: -0.1700
Data Index: 28014 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8009. Min Range: -5.8009
Max Act: 5.4884. Min Act: -0.1700
Data Index: 3533873 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19