Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2709 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.6218. Min Act: -0.1700
Data Index: 693766 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.5905. Min Act: -0.1700
Data Index: 1127931 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.5905. Min Act: -0.1700
Data Index: 1576872 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.5593. Min Act: -0.1700
Data Index: 3842088 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.5280. Min Act: -0.1700
Data Index: 6383966 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.5905. Min Act: -0.1700
Data Index: 2807700 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.5280. Min Act: -0.1700
Data Index: 3439923 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.5280. Min Act: -0.1700
Data Index: 579660 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.5280. Min Act: -0.1700
Data Index: 2706993 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4968. Min Act: -0.1700
Data Index: 5111694 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4655. Min Act: -0.1700
Data Index: 5470859 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4968. Min Act: -0.1700
Data Index: 803787 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4968. Min Act: -0.1700
Data Index: 8295140 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4343. Min Act: -0.1700
Data Index: 7816122 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4655. Min Act: -0.1700
Data Index: 5461476 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4343. Min Act: -0.1700
Data Index: 5392353 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4655. Min Act: -0.1700
Data Index: 7131575 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4343. Min Act: -0.1700
Data Index: 4007385 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4655. Min Act: -0.1700
Data Index: 7252918 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6218. Min Range: -4.6218
Max Act: 4.4343. Min Act: -0.1700
Data Index: 6177670 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19