Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3809 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.5572. Min Act: -0.1700
Data Index: 2351254 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.5572. Min Act: -0.1700
Data Index: 1507908 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.5260. Min Act: -0.1700
Data Index: 1263107 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.5260. Min Act: -0.1700
Data Index: 3098828 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.5260. Min Act: -0.1700
Data Index: 6349875 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.4322. Min Act: -0.1700
Data Index: 4498761 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.4634. Min Act: -0.1700
Data Index: 5066304 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.4009. Min Act: -0.1700
Data Index: 5449396 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.4009. Min Act: -0.1700
Data Index: 8313525 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.4322. Min Act: -0.1700
Data Index: 7439176 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.4009. Min Act: -0.1700
Data Index: 4414991 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.4009. Min Act: -0.1700
Data Index: 8518096 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.4322. Min Act: -0.1700
Data Index: 462705 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.3697. Min Act: -0.1700
Data Index: 5435412 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.3697. Min Act: -0.1700
Data Index: 3923682 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.3697. Min Act: -0.1700
Data Index: 2333755 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.3697. Min Act: -0.1700
Data Index: 7863903 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.3697. Min Act: -0.1700
Data Index: 2348053 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.3384. Min Act: -0.1700
Data Index: 3210573 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5572. Min Range: -4.5572
Max Act: 4.3384. Min Act: -0.1700
Data Index: 4385600 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19