Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5092 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1821. Min Range: -4.1821
Max Act: 4.1821. Min Act: -0.1700
Data Index: 8775438 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1821. Min Range: -4.1821
Max Act: 4.0883. Min Act: -0.1700
Data Index: 3969338 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1821. Min Range: -4.1821
Max Act: 4.0570. Min Act: -0.1700
Data Index: 4701357 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1821. Min Range: -4.1821
Max Act: 4.0570. Min Act: -0.1700
Data Index: 3267884 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1821. Min Range: -4.1821
Max Act: 4.0258. Min Act: -0.1700
Data Index: 4802937 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1821. Min Range: -4.1821
Max Act: 4.0258. Min Act: -0.1700
Data Index: 2896942 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9945. Min Act: -0.1700
Data Index: 6632786 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1821. Min Range: -4.1821
Max Act: 4.0258. Min Act: -0.1700
Data Index: 6104571 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9945. Min Act: -0.1700
Data Index: 1356149 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9945. Min Act: -0.1700
Data Index: 6030572 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9945. Min Act: -0.1700
Data Index: 6703395 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9633. Min Act: -0.1700
Data Index: 497414 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9320. Min Act: -0.1700
Data Index: 8389354 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9320. Min Act: -0.1700
Data Index: 8322436 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9320. Min Act: -0.1700
Data Index: 3822748 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9007. Min Act: -0.1700
Data Index: 627112 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9007. Min Act: -0.1700
Data Index: 7732272 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.9007. Min Act: -0.1700
Data Index: 7808133 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.8695. Min Act: -0.1700
Data Index: 1039374 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1821. Min Range: -4.1821
Max Act: 3.8695. Min Act: -0.1700
Data Index: 4330592 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19