Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5850 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.7826. Min Act: -0.1700
Data Index: 6747231 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.7513. Min Act: -0.1700
Data Index: 4752061 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.5638. Min Act: -0.1700
Data Index: 4824596 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.5326. Min Act: -0.1700
Data Index: 6807108 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.4076. Min Act: -0.1700
Data Index: 6224043 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.4076. Min Act: -0.1700
Data Index: 8097706 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.3450. Min Act: -0.1700
Data Index: 8397257 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.3450. Min Act: -0.1700
Data Index: 1187471 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.2825. Min Act: -0.1700
Data Index: 3151601 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.3138. Min Act: -0.1700
Data Index: 4740715 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.3138. Min Act: -0.1700
Data Index: 2805967 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.3138. Min Act: -0.1700
Data Index: 4889519 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.3138. Min Act: -0.1700
Data Index: 4799337 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.3138. Min Act: -0.1700
Data Index: 6912109 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.3138. Min Act: -0.1700
Data Index: 245315 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.2825. Min Act: -0.1700
Data Index: 1045348 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.2825. Min Act: -0.1700
Data Index: 6296182 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.2825. Min Act: -0.1700
Data Index: 3233884 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.2513. Min Act: -0.1700
Data Index: 2275998 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7826. Min Range: -4.7826
Max Act: 4.2513. Min Act: -0.1700
Data Index: 6187004 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19