Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.3010. Min Act: -0.1700
Data Index: 561576 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.3010. Min Act: -0.1700
Data Index: 2857984 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.3010. Min Act: -0.1700
Data Index: 3269775 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.3010. Min Act: -0.1700
Data Index: 8440782 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2697. Min Act: -0.1700
Data Index: 6730156 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2697. Min Act: -0.1700
Data Index: 7929758 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2385. Min Act: -0.1700
Data Index: 862702 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2385. Min Act: -0.1700
Data Index: 8111744 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2385. Min Act: -0.1700
Data Index: 2342491 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2697. Min Act: -0.1700
Data Index: 5223346 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.3010. Min Act: -0.1700
Data Index: 5159649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2697. Min Act: -0.1700
Data Index: 5191450 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2697. Min Act: -0.1700
Data Index: 387316 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2697. Min Act: -0.1700
Data Index: 388691 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2697. Min Act: -0.1700
Data Index: 975598 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2385. Min Act: -0.1700
Data Index: 1053910 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2385. Min Act: -0.1700
Data Index: 3324846 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2385. Min Act: -0.1700
Data Index: 939685 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2385. Min Act: -0.1700
Data Index: 910871 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3010. Min Range: -4.3010
Max Act: 4.2385. Min Act: -0.1700
Data Index: 2810037 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19