Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 905 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.5229. Min Act: -0.1700
Data Index: 1096723 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.5542. Min Act: -0.1700
Data Index: 257637 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.4604. Min Act: -0.1700
Data Index: 1381896 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.3354. Min Act: -0.1700
Data Index: 277488 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.2417. Min Act: -0.1700
Data Index: 202879 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.2729. Min Act: -0.1700
Data Index: 3883479 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.2729. Min Act: -0.1700
Data Index: 1369730 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.2417. Min Act: -0.1700
Data Index: 6267557 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.2417. Min Act: -0.1700
Data Index: 681371 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.2104. Min Act: -0.1700
Data Index: 1093855 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.2104. Min Act: -0.1700
Data Index: 1254022 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.1792. Min Act: -0.1700
Data Index: 6148706 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.1792. Min Act: -0.1700
Data Index: 2458697 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.1792. Min Act: -0.1700
Data Index: 5774338 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.1792. Min Act: -0.1700
Data Index: 900832 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.1167. Min Act: -0.1700
Data Index: 1169802 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.0854. Min Act: -0.1700
Data Index: 4022972 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.0854. Min Act: -0.1700
Data Index: 2257081 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.0542. Min Act: -0.1700
Data Index: 5047833 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5542. Min Range: -6.5542
Max Act: 6.1167. Min Act: -0.1700
Data Index: 347280 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19