Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1511 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0352. Min Range: -6.0352
Max Act: 6.0352. Min Act: -0.1700
Data Index: 4190140 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0352. Min Range: -6.0352
Max Act: 6.0040. Min Act: -0.1700
Data Index: 3692075 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.9102. Min Act: -0.1700
Data Index: 879868 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.7540. Min Act: -0.1700
Data Index: 1803738 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.7227. Min Act: -0.1698
Data Index: 8121254 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.7540. Min Act: -0.1700
Data Index: 7942224 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.7852. Min Act: -0.1700
Data Index: 4761131 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.7227. Min Act: -0.1700
Data Index: 152130 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.6915. Min Act: -0.1700
Data Index: 4617362 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.7227. Min Act: -0.1700
Data Index: 2610558 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.6602. Min Act: -0.1699
Data Index: 4810735 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.6915. Min Act: -0.1700
Data Index: 8225002 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.6602. Min Act: -0.1700
Data Index: 4927518 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.5977. Min Act: -0.1700
Data Index: 4456385 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.5977. Min Act: -0.1700
Data Index: 1966225 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.5977. Min Act: -0.1700
Data Index: 5733785 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.5977. Min Act: -0.1700
Data Index: 4676911 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.5977. Min Act: -0.1700
Data Index: 8573137 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.5040. Min Act: -0.1700
Data Index: 1880744 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0352. Min Range: -6.0352
Max Act: 5.5040. Min Act: -0.1700
Data Index: 6860134 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19