Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.5272. Min Act: -0.1700
Data Index: 7891305 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.2772. Min Act: -0.1700
Data Index: 1223924 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.2772. Min Act: -0.1700
Data Index: 6204215 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.2772. Min Act: -0.1700
Data Index: 2648082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.2147. Min Act: -0.1700
Data Index: 4859702 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.1834. Min Act: -0.1700
Data Index: 8576457 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.1834. Min Act: -0.1700
Data Index: 4260626 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.1834. Min Act: -0.1700
Data Index: 1968852 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.1834. Min Act: -0.1700
Data Index: 7166759 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.1834. Min Act: -0.1700
Data Index: 3783196 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.1209. Min Act: -0.1700
Data Index: 866283 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.1209. Min Act: -0.1700
Data Index: 752789 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.0897. Min Act: -0.1700
Data Index: 8077889 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.0584. Min Act: -0.1700
Data Index: 7421800 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.0897. Min Act: -0.1700
Data Index: 4899888 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5272. Min Range: -5.5272
Max Act: 4.9959. Min Act: -0.1700
Data Index: 4455310 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5272. Min Range: -5.5272
Max Act: 4.9959. Min Act: -0.1700
Data Index: 3531372 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5272. Min Range: -5.5272
Max Act: 5.0272. Min Act: -0.1700
Data Index: 3291184 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5272. Min Range: -5.5272
Max Act: 4.9647. Min Act: -0.1700
Data Index: 6945706 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5272. Min Range: -5.5272
Max Act: 4.9959. Min Act: -0.1700
Data Index: 2588403 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19