Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.7539. Min Act: -0.1700
Data Index: 698206 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.7539. Min Act: -0.1700
Data Index: 5226711 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.6602. Min Act: -0.1700
Data Index: 244767 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.5039. Min Act: -0.1700
Data Index: 244766 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.3477. Min Act: -0.1700
Data Index: 4734600 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.3477. Min Act: -0.1700
Data Index: 32028 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.3164. Min Act: -0.1700
Data Index: 4226238 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.1914. Min Act: -0.1700
Data Index: 3679859 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.1914. Min Act: -0.1700
Data Index: 4734602 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.1602. Min Act: -0.1700
Data Index: 2328294 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.1602. Min Act: -0.1700
Data Index: 281241 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.1602. Min Act: -0.1700
Data Index: 5934179 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.0977. Min Act: -0.1700
Data Index: 1281986 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.0664. Min Act: -0.1700
Data Index: 7692402 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.0664. Min Act: -0.1700
Data Index: 1011959 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.0664. Min Act: -0.1700
Data Index: 8628020 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.0352. Min Act: -0.1700
Data Index: 7105110 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.0352. Min Act: -0.1700
Data Index: 4250407 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.0352. Min Act: -0.1700
Data Index: 8695396 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7539. Min Range: -5.7539
Max Act: 5.0039. Min Act: -0.1700
Data Index: 4139666 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19