Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3951 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.6603. Min Act: -0.1700
Data Index: 3308604 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.5664. Min Act: -0.1700
Data Index: 1248704 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.5194. Min Act: -0.1700
Data Index: 3308605 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4881. Min Act: -0.1700
Data Index: 3038272 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.5037. Min Act: -0.1700
Data Index: 4394187 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4881. Min Act: -0.1700
Data Index: 7228641 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4724. Min Act: -0.1700
Data Index: 4655731 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4724. Min Act: -0.1700
Data Index: 379923 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4724. Min Act: -0.1700
Data Index: 1820307 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4567. Min Act: -0.1700
Data Index: 5753428 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4567. Min Act: -0.1700
Data Index: 2451261 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4411. Min Act: -0.1700
Data Index: 1273933 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4411. Min Act: -0.1700
Data Index: 6477623 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4411. Min Act: -0.1700
Data Index: 3308603 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4411. Min Act: -0.1700
Data Index: 5506867 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4411. Min Act: -0.1700
Data Index: 1197822 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4254. Min Act: -0.1700
Data Index: 4655728 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4097. Min Act: -0.1700
Data Index: 1474742 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4097. Min Act: -0.1700
Data Index: 578374 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6603. Min Range: -3.6603
Max Act: 3.4097. Min Act: -0.1700
Data Index: 2051332 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19