Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2597 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0731. Min Range: -7.0731
Max Act: 7.0731. Min Act: -0.1700
Data Index: 5670586 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.9168. Min Act: -0.1700
Data Index: 7492988 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.8856. Min Act: -0.1700
Data Index: 3146636 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.9168. Min Act: -0.1700
Data Index: 1401182 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.8543. Min Act: -0.1700
Data Index: 3640547 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.6981. Min Act: -0.1700
Data Index: 3681563 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.6356. Min Act: -0.1700
Data Index: 2149707 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.5106. Min Act: -0.1700
Data Index: 747344 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.5106. Min Act: -0.1700
Data Index: 4784636 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.4481. Min Act: -0.1700
Data Index: 4416153 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.4168. Min Act: -0.1700
Data Index: 4220886 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.4793. Min Act: -0.1700
Data Index: 385746 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 8460732 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.3856. Min Act: -0.1700
Data Index: 5204434 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.3856. Min Act: -0.1700
Data Index: 8100067 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.3231. Min Act: -0.1700
Data Index: 3087491 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 6063020 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.3543. Min Act: -0.1700
Data Index: 640261 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.3231. Min Act: -0.1700
Data Index: 5801538 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0731. Min Range: -7.0731
Max Act: 6.3231. Min Act: -0.1700
Data Index: 2103817 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19