Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 891 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.7726. Min Act: -0.1700
Data Index: 4503239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.7726. Min Act: -0.1700
Data Index: 2324913 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.6476. Min Act: -0.1700
Data Index: 6475573 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.6476. Min Act: -0.1700
Data Index: 7583139 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.6476. Min Act: -0.1700
Data Index: 8215051 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5851. Min Act: -0.1700
Data Index: 3666531 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.6476. Min Act: -0.1700
Data Index: 2235272 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5851. Min Act: -0.1700
Data Index: 4933786 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5851. Min Act: -0.1700
Data Index: 3611120 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5226. Min Act: -0.1700
Data Index: 2531343 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5226. Min Act: -0.1700
Data Index: 3967151 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5226. Min Act: -0.1700
Data Index: 2531329 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5226. Min Act: -0.1700
Data Index: 2531344 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.4601. Min Act: -0.1700
Data Index: 2056934 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.4601. Min Act: -0.1700
Data Index: 4234521 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5851. Min Act: -0.1700
Data Index: 1537509 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.4601. Min Act: -0.1700
Data Index: 4183270 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5226. Min Act: -0.1700
Data Index: 2013554 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.4601. Min Act: -0.1700
Data Index: 3895647 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7726. Min Range: -10.7726
Max Act: 10.5226. Min Act: -0.1700
Data Index: 3574231 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19