Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.1810. Min Act: -0.1700
Data Index: 4204676 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.1643. Min Act: -0.1700
Data Index: 5418589 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0808. Min Act: -0.1700
Data Index: 7507285 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0640. Min Act: -0.1700
Data Index: 726775 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0472. Min Act: -0.1700
Data Index: 415936 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0640. Min Act: -0.1700
Data Index: 8563778 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0640. Min Act: -0.1700
Data Index: 6250973 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0472. Min Act: -0.1700
Data Index: 4546931 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0472. Min Act: -0.1700
Data Index: 4576435 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0303. Min Act: -0.1700
Data Index: 7756478 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0135. Min Act: -0.1700
Data Index: 3549866 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0135. Min Act: -0.1700
Data Index: 3516974 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1810. Min Range: -2.1810
Max Act: 2.0303. Min Act: -0.1700
Data Index: 2075120 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1810. Min Range: -2.1810
Max Act: 1.9966. Min Act: -0.1700
Data Index: 4246968 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1810. Min Range: -2.1810
Max Act: 1.9966. Min Act: -0.1700
Data Index: 3585229 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1810. Min Range: -2.1810
Max Act: 1.9966. Min Act: -0.1700
Data Index: 6209535 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1810. Min Range: -2.1810
Max Act: 1.9966. Min Act: -0.1700
Data Index: 4559882 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1810. Min Range: -2.1810
Max Act: 1.9966. Min Act: -0.1700
Data Index: 4749252 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1810. Min Range: -2.1810
Max Act: 1.9966. Min Act: -0.1700
Data Index: 2756494 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1810. Min Range: -2.1810
Max Act: 1.9966. Min Act: -0.1700
Data Index: 3141235 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19