Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.6515. Min Act: -0.1700
Data Index: 1502516 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.5577. Min Act: -0.1700
Data Index: 4117597 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.5265. Min Act: -0.1700
Data Index: 1455104 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.4327. Min Act: -0.1700
Data Index: 4209354 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.4015. Min Act: -0.1700
Data Index: 4526703 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.4015. Min Act: -0.1700
Data Index: 2396904 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.4015. Min Act: -0.1700
Data Index: 1022506 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.3702. Min Act: -0.1700
Data Index: 7161232 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.3702. Min Act: -0.1700
Data Index: 1455102 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.3390. Min Act: -0.1700
Data Index: 4117602 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.3390. Min Act: -0.1700
Data Index: 3879767 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.3390. Min Act: -0.1700
Data Index: 6537424 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.3077. Min Act: -0.1700
Data Index: 883976 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.3077. Min Act: -0.1700
Data Index: 1320954 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.2765. Min Act: -0.1700
Data Index: 5847809 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.2765. Min Act: -0.1700
Data Index: 4299675 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.2452. Min Act: -0.1700
Data Index: 6166280 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.2765. Min Act: -0.1700
Data Index: 2136056 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.2452. Min Act: -0.1700
Data Index: 3709334 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6515. Min Range: -4.6515
Max Act: 4.2140. Min Act: -0.1700
Data Index: 6426399 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19