Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3588 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.4848. Min Act: -0.1700
Data Index: 6863819 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.4223. Min Act: -0.1700
Data Index: 7369967 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.2973. Min Act: -0.1700
Data Index: 2605748 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.2973. Min Act: -0.1700
Data Index: 4986504 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.2973. Min Act: -0.1700
Data Index: 7006355 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.2348. Min Act: -0.1700
Data Index: 5832081 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.2348. Min Act: -0.1700
Data Index: 4872373 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.1723. Min Act: -0.1700
Data Index: 2461903 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.1723. Min Act: -0.1700
Data Index: 1334838 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.1723. Min Act: -0.1700
Data Index: 8728425 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.1723. Min Act: -0.1700
Data Index: 5688681 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.1723. Min Act: -0.1700
Data Index: 7512193 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.0473. Min Act: -0.1700
Data Index: 4518720 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.1098. Min Act: -0.1700
Data Index: 7020483 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.1098. Min Act: -0.1700
Data Index: 2483687 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.1098. Min Act: -0.1700
Data Index: 1405018 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.0473. Min Act: -0.1700
Data Index: 4333323 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4848. Min Range: -8.4848
Max Act: 7.9848. Min Act: -0.1700
Data Index: 3863672 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.0473. Min Act: -0.1700
Data Index: 1038119 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4848. Min Range: -8.4848
Max Act: 8.0473. Min Act: -0.1700
Data Index: 6954610 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19