Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1108 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.5044. Min Act: -0.1700
Data Index: 446748 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.4731. Min Act: -0.1700
Data Index: 3795997 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.3947. Min Act: -0.1700
Data Index: 1041732 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.3791. Min Act: -0.1700
Data Index: 7557142 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.3634. Min Act: -0.1700
Data Index: 6239588 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.3163. Min Act: -0.1700
Data Index: 5244744 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2849. Min Act: -0.1700
Data Index: 1492848 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2535. Min Act: -0.1700
Data Index: 4536030 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2535. Min Act: -0.1700
Data Index: 3457060 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2535. Min Act: -0.1700
Data Index: 8270850 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2378. Min Act: -0.1700
Data Index: 3286600 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2378. Min Act: -0.1700
Data Index: 238462 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2221. Min Act: -0.1700
Data Index: 4102967 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2221. Min Act: -0.1700
Data Index: 4304686 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2063. Min Act: -0.1700
Data Index: 6542507 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2063. Min Act: -0.1700
Data Index: 5183809 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.1906. Min Act: -0.1700
Data Index: 1694342 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.1906. Min Act: -0.1700
Data Index: 3178190 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.2063. Min Act: -0.1700
Data Index: 5598685 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5044. Min Range: -3.5044
Max Act: 3.1749. Min Act: -0.1700
Data Index: 1264005 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19