Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2191 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.7777. Min Act: -0.1700
Data Index: 1632100 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.6527. Min Act: -0.1700
Data Index: 8282154 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.5902. Min Act: -0.1700
Data Index: 2665630 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.5590. Min Act: -0.1700
Data Index: 2014182 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.4965. Min Act: -0.1700
Data Index: 3395860 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.4652. Min Act: -0.1700
Data Index: 6193467 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.4340. Min Act: -0.1700
Data Index: 4047730 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.3402. Min Act: -0.1700
Data Index: 195544 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.3402. Min Act: -0.1700
Data Index: 2423078 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.3402. Min Act: -0.1700
Data Index: 4447100 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.3090. Min Act: -0.1700
Data Index: 3891699 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.3090. Min Act: -0.1700
Data Index: 3140018 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.3090. Min Act: -0.1700
Data Index: 700728 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.3090. Min Act: -0.1700
Data Index: 654353 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.3090. Min Act: -0.1700
Data Index: 2250852 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.2777. Min Act: -0.1700
Data Index: 3992227 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.2777. Min Act: -0.1700
Data Index: 2250854 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.2777. Min Act: -0.1700
Data Index: 3551381 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.2777. Min Act: -0.1700
Data Index: 5201601 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7777. Min Range: -7.7777
Max Act: 7.2777. Min Act: -0.1700
Data Index: 1158964 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19