Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3452 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.3301. Min Act: -0.1700
Data Index: 1399873 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.3144. Min Act: -0.1700
Data Index: 3534932 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.2673. Min Act: -0.1700
Data Index: 1394966 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.2673. Min Act: -0.1700
Data Index: 7051137 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.2516. Min Act: -0.1700
Data Index: 3646340 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.2201. Min Act: -0.1700
Data Index: 8198691 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 5778966 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 3034408 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 4698729 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.2044. Min Act: -0.1700
Data Index: 913948 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 3453445 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 6067440 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 6032265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 5393417 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 2901040 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 7376725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1887. Min Act: -0.1700
Data Index: 6900732 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1729. Min Act: -0.1700
Data Index: 8426721 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1729. Min Act: -0.1700
Data Index: 5530597 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3301. Min Range: -3.3301
Max Act: 3.1572. Min Act: -0.1700
Data Index: 6900733 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19