Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4804 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.5441. Min Act: -0.1700
Data Index: 6826344 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.4191. Min Act: -0.1700
Data Index: 4959157 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.3566. Min Act: -0.1700
Data Index: 646221 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.3566. Min Act: -0.1700
Data Index: 2920666 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.3253. Min Act: -0.1700
Data Index: 2587970 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.2315. Min Act: -0.1700
Data Index: 6788555 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.2003. Min Act: -0.1700
Data Index: 3691901 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.2003. Min Act: -0.1700
Data Index: 883894 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1690. Min Act: -0.1700
Data Index: 1921648 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1690. Min Act: -0.1700
Data Index: 5177142 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1690. Min Act: -0.1700
Data Index: 8637004 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1378. Min Act: -0.1700
Data Index: 2613803 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1378. Min Act: -0.1700
Data Index: 7910378 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1378. Min Act: -0.1700
Data Index: 8496352 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1065. Min Act: -0.1700
Data Index: 3412804 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1065. Min Act: -0.1700
Data Index: 7683914 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1065. Min Act: -0.1700
Data Index: 4442121 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.0753. Min Act: -0.1700
Data Index: 2681754 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.1065. Min Act: -0.1700
Data Index: 373013 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5441. Min Range: -4.5441
Max Act: 4.0753. Min Act: -0.1700
Data Index: 6753479 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19