Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.4748. Min Act: -0.1700
Data Index: 756996 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.3811. Min Act: -0.1700
Data Index: 7498632 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.3498. Min Act: -0.1700
Data Index: 277819 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.3498. Min Act: -0.1700
Data Index: 2881754 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.3498. Min Act: -0.1700
Data Index: 4431741 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.3186. Min Act: -0.1700
Data Index: 5183073 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.3186. Min Act: -0.1700
Data Index: 403168 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.3498. Min Act: -0.1700
Data Index: 6959126 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 4920102 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 999572 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 1917409 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 2806729 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 3901942 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 6448182 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 277818 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 2537116 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 5778960 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 3768636 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2873. Min Act: -0.1700
Data Index: 3988610 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4748. Min Range: -5.4748
Max Act: 5.2561. Min Act: -0.1700
Data Index: 3909478 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19