Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2632 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.4084. Min Act: -0.1700
Data Index: 2810331 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.4396. Min Act: -0.1700
Data Index: 7587973 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.4084. Min Act: -0.1700
Data Index: 40030 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.3459. Min Act: -0.1700
Data Index: 5831672 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.3771. Min Act: -0.1700
Data Index: 3994487 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.3146. Min Act: -0.1700
Data Index: 1949871 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.3146. Min Act: -0.1700
Data Index: 3604014 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.3146. Min Act: -0.1700
Data Index: 2832737 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.3146. Min Act: -0.1700
Data Index: 336291 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.3459. Min Act: -0.1700
Data Index: 1438279 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.2834. Min Act: -0.1700
Data Index: 902784 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.2521. Min Act: -0.1700
Data Index: 4402180 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.2209. Min Act: -0.1700
Data Index: 1329163 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.2209. Min Act: -0.1700
Data Index: 879922 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.1896. Min Act: -0.1700
Data Index: 3896906 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.1896. Min Act: -0.1700
Data Index: 3924469 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.1896. Min Act: -0.1700
Data Index: 933514 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.1896. Min Act: -0.1700
Data Index: 2935904 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.2209. Min Act: -0.1700
Data Index: 699834 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4396. Min Range: -5.4396
Max Act: 5.2209. Min Act: -0.1700
Data Index: 3268995 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19