Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.5067. Min Act: -0.1700
Data Index: 3098879 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.3505. Min Act: -0.1700
Data Index: 2705404 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.2567. Min Act: -0.1700
Data Index: 8105958 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.2567. Min Act: -0.1698
Data Index: 133979 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1942. Min Act: -0.1700
Data Index: 2211046 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1942. Min Act: -0.1700
Data Index: 7802576 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1942. Min Act: -0.1700
Data Index: 119186 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1942. Min Act: -0.1700
Data Index: 3451731 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1630. Min Act: -0.1700
Data Index: 7498845 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1630. Min Act: -0.1700
Data Index: 4563638 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1630. Min Act: -0.1700
Data Index: 1252424 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1630. Min Act: -0.1700
Data Index: 878869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1630. Min Act: -0.1700
Data Index: 4380527 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1317. Min Act: -0.1700
Data Index: 4270658 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1317. Min Act: -0.1700
Data Index: 2783543 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1317. Min Act: -0.1700
Data Index: 6756734 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1005. Min Act: -0.1700
Data Index: 4567360 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1317. Min Act: -0.1700
Data Index: 655425 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1005. Min Act: -0.1700
Data Index: 2728063 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5067. Min Range: -4.5067
Max Act: 4.1005. Min Act: -0.1700
Data Index: 7657169 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19