Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1780 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.6134. Min Act: -0.1700
Data Index: 7811026 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.5822. Min Act: -0.1700
Data Index: 1683226 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.5509. Min Act: -0.1700
Data Index: 4056840 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.5197. Min Act: -0.1700
Data Index: 3553422 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.4572. Min Act: -0.1700
Data Index: 1053882 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.3947. Min Act: -0.1700
Data Index: 1974390 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.3947. Min Act: -0.1700
Data Index: 1225078 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.3634. Min Act: -0.1700
Data Index: 4371096 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.3634. Min Act: -0.1700
Data Index: 7282834 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.3009. Min Act: -0.1700
Data Index: 1595733 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.3009. Min Act: -0.1700
Data Index: 7398445 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.3322. Min Act: -0.1700
Data Index: 8620466 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.3009. Min Act: -0.1700
Data Index: 3365225 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.2697. Min Act: -0.1700
Data Index: 1383902 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.2697. Min Act: -0.1700
Data Index: 6582611 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.2697. Min Act: -0.1700
Data Index: 3535163 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.2384. Min Act: -0.1700
Data Index: 4518323 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.2072. Min Act: -0.1700
Data Index: 3867767 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.2697. Min Act: -0.1700
Data Index: 1790611 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6134. Min Range: -4.6134
Max Act: 4.2384. Min Act: -0.1700
Data Index: 5226809 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19