Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.4422. Min Act: -0.1700
Data Index: 1364870 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.3484. Min Act: -0.1700
Data Index: 1220747 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.2859. Min Act: -0.1700
Data Index: 2550277 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.2859. Min Act: -0.1700
Data Index: 3914607 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.2859. Min Act: -0.1700
Data Index: 653772 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.2234. Min Act: -0.1700
Data Index: 2467415 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.2234. Min Act: -0.1700
Data Index: 8308843 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1922. Min Act: -0.1700
Data Index: 795879 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.2234. Min Act: -0.1700
Data Index: 341184 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1922. Min Act: -0.1700
Data Index: 1455775 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1922. Min Act: -0.1700
Data Index: 5881938 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1922. Min Act: -0.1700
Data Index: 3647868 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1922. Min Act: -0.1700
Data Index: 5877931 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1609. Min Act: -0.1700
Data Index: 7338407 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1609. Min Act: -0.1700
Data Index: 6279375 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1609. Min Act: -0.1700
Data Index: 2776079 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1609. Min Act: -0.1700
Data Index: 2610392 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1609. Min Act: -0.1699
Data Index: 5729896 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1609. Min Act: -0.1700
Data Index: 1584408 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4422. Min Range: -6.4422
Max Act: 6.1609. Min Act: -0.1700
Data Index: 6255061 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19