Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.2061. Min Act: -0.1700
Data Index: 2150603 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.1749. Min Act: -0.1700
Data Index: 7231195 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.1436. Min Act: -0.1700
Data Index: 5333714 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.1123. Min Act: -0.1700
Data Index: 3069776 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.1123. Min Act: -0.1700
Data Index: 2934843 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.0498. Min Act: -0.1700
Data Index: 1716423 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.0498. Min Act: -0.1700
Data Index: 115141 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.0498. Min Act: -0.1700
Data Index: 1927999 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.0186. Min Act: -0.1700
Data Index: 4022643 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.0186. Min Act: -0.1700
Data Index: 6224033 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2061. Min Range: -4.2061
Max Act: 4.0186. Min Act: -0.1700
Data Index: 8198406 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9873. Min Act: -0.1700
Data Index: 4563115 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9873. Min Act: -0.1700
Data Index: 3561878 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9561. Min Act: -0.1700
Data Index: 3149957 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9561. Min Act: -0.1700
Data Index: 3297026 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9561. Min Act: -0.1700
Data Index: 5565810 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9561. Min Act: -0.1700
Data Index: 574786 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9561. Min Act: -0.1700
Data Index: 8619822 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9561. Min Act: -0.1700
Data Index: 5352246 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2061. Min Range: -4.2061
Max Act: 3.9248. Min Act: -0.1700
Data Index: 6074225 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19