Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 934 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1484. Min Range: -6.1484
Max Act: 6.1484. Min Act: -0.1700
Data Index: 4541921 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1484. Min Range: -6.1484
Max Act: 6.0859. Min Act: -0.1700
Data Index: 8816300 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1484. Min Range: -6.1484
Max Act: 6.0234. Min Act: -0.1700
Data Index: 2305757 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1484. Min Range: -6.1484
Max Act: 6.0234. Min Act: -0.1700
Data Index: 8699641 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.9609. Min Act: -0.1700
Data Index: 1539555 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.9609. Min Act: -0.1700
Data Index: 8414967 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.8672. Min Act: -0.1700
Data Index: 5385811 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.8672. Min Act: -0.1700
Data Index: 7834529 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.8984. Min Act: -0.1700
Data Index: 4087481 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.8047. Min Act: -0.1700
Data Index: 3817090 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.8047. Min Act: -0.1700
Data Index: 8645484 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.8359. Min Act: -0.1700
Data Index: 6954338 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.7734. Min Act: -0.1700
Data Index: 566816 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.7422. Min Act: -0.1700
Data Index: 3017198 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.8047. Min Act: -0.1700
Data Index: 1086876 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.7734. Min Act: -0.1700
Data Index: 2705714 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.7109. Min Act: -0.1700
Data Index: 6178190 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.7734. Min Act: -0.1700
Data Index: 8700449 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.7734. Min Act: -0.1700
Data Index: 6399267 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1484. Min Range: -6.1484
Max Act: 5.7422. Min Act: -0.1700
Data Index: 2852063 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19