Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 215 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.8973. Min Act: -0.1700
Data Index: 5978227 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.8497. Min Act: -0.1700
Data Index: 357318 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.8497. Min Act: -0.1700
Data Index: 7709522 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7861. Min Act: -0.1700
Data Index: 7257913 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.8020. Min Act: -0.1700
Data Index: 888234 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7701. Min Act: -0.1700
Data Index: 3820975 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7861. Min Act: -0.1700
Data Index: 4508368 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7542. Min Act: -0.1700
Data Index: 6414005 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7701. Min Act: -0.1700
Data Index: 1336378 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7701. Min Act: -0.1700
Data Index: 2204460 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7701. Min Act: -0.1700
Data Index: 889999 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7701. Min Act: -0.1700
Data Index: 8486685 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7542. Min Act: -0.1700
Data Index: 2366336 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7542. Min Act: -0.1700
Data Index: 4460242 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7542. Min Act: -0.1700
Data Index: 7502368 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7542. Min Act: -0.1700
Data Index: 595196 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7542. Min Act: -0.1700
Data Index: 4655527 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7542. Min Act: -0.1700
Data Index: 2114164 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7542. Min Act: -0.1700
Data Index: 3308259 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8973. Min Range: -2.8973
Max Act: 2.7382. Min Act: -0.1700
Data Index: 813111 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19