Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1050 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.4446. Min Act: -0.1700
Data Index: 8493598 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.4133. Min Act: -0.1700
Data Index: 8499575 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.2570. Min Act: -0.1700
Data Index: 7611239 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.2258. Min Act: -0.1700
Data Index: 7735040 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.1945. Min Act: -0.1700
Data Index: 8595305 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.1945. Min Act: -0.1700
Data Index: 3547564 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0695. Min Act: -0.1700
Data Index: 6416699 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.1008. Min Act: -0.1700
Data Index: 3429428 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0695. Min Act: -0.1700
Data Index: 6018615 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0383. Min Act: -0.1700
Data Index: 808822 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0695. Min Act: -0.1700
Data Index: 6093344 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0383. Min Act: -0.1700
Data Index: 165642 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0695. Min Act: -0.1700
Data Index: 3558805 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0383. Min Act: -0.1700
Data Index: 1274832 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0383. Min Act: -0.1700
Data Index: 2980232 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0695. Min Act: -0.1700
Data Index: 357500 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0695. Min Act: -0.1700
Data Index: 4470578 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0070. Min Act: -0.1700
Data Index: 1957656 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0070. Min Act: -0.1700
Data Index: 5358802 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4446. Min Range: -4.4446
Max Act: 4.0070. Min Act: -0.1700
Data Index: 6047256 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19