Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 859 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5878. Min Range: -4.5878
Max Act: 4.5878. Min Act: -0.1700
Data Index: 4777669 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5878. Min Range: -4.5878
Max Act: 4.3065. Min Act: -0.1700
Data Index: 1190996 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5878. Min Range: -4.5878
Max Act: 4.2753. Min Act: -0.1700
Data Index: 2679674 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5878. Min Range: -4.5878
Max Act: 4.0252. Min Act: -0.1700
Data Index: 4487140 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9940. Min Act: -0.1700
Data Index: 8808660 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9627. Min Act: -0.1700
Data Index: 5671529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9627. Min Act: -0.1700
Data Index: 2785893 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9627. Min Act: -0.1700
Data Index: 8787784 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9627. Min Act: -0.1700
Data Index: 880380 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9627. Min Act: -0.1700
Data Index: 4814491 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9627. Min Act: -0.1700
Data Index: 4380430 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9627. Min Act: -0.1700
Data Index: 1500252 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9002. Min Act: -0.1700
Data Index: 507872 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9002. Min Act: -0.1700
Data Index: 6047346 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9002. Min Act: -0.1700
Data Index: 3633023 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9002. Min Act: -0.1700
Data Index: 6361879 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9002. Min Act: -0.1700
Data Index: 4751767 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9002. Min Act: -0.1700
Data Index: 6939974 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9002. Min Act: -0.1700
Data Index: 1848336 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5878. Min Range: -4.5878
Max Act: 3.9002. Min Act: -0.1700
Data Index: 8730043 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19