Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4921 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.5950. Min Act: -0.1700
Data Index: 6465424 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.3763. Min Act: -0.1700
Data Index: 137512 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.3450. Min Act: -0.1700
Data Index: 3677592 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.3450. Min Act: -0.1700
Data Index: 3559876 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.2825. Min Act: -0.1700
Data Index: 1707065 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.2825. Min Act: -0.1700
Data Index: 6868290 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.2513. Min Act: -0.1700
Data Index: 6185274 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.2513. Min Act: -0.1700
Data Index: 5390990 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.1888. Min Act: -0.1700
Data Index: 5984250 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.1575. Min Act: -0.1700
Data Index: 2363426 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.1575. Min Act: -0.1700
Data Index: 4880466 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.1263. Min Act: -0.1700
Data Index: 5012958 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.1263. Min Act: -0.1700
Data Index: 519585 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.1575. Min Act: -0.1700
Data Index: 3316234 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.1263. Min Act: -0.1700
Data Index: 5720510 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.1263. Min Act: -0.1700
Data Index: 1285410 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.0950. Min Act: -0.1700
Data Index: 5164993 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.0638. Min Act: -0.1700
Data Index: 1912368 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.0638. Min Act: -0.1700
Data Index: 5440081 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5950. Min Range: -6.5950
Max Act: 6.0950. Min Act: -0.1700
Data Index: 6491240 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19