Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1831 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1637. Min Range: -5.1637
Max Act: 5.1637. Min Act: -0.1700
Data Index: 1585264 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1637. Min Range: -5.1637
Max Act: 5.0699. Min Act: -0.1700
Data Index: 5598290 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1637. Min Range: -5.1637
Max Act: 5.0074. Min Act: -0.1700
Data Index: 6879054 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9762. Min Act: -0.1700
Data Index: 4553847 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9449. Min Act: -0.1700
Data Index: 1334519 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9449. Min Act: -0.1700
Data Index: 8525091 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9137. Min Act: -0.1700
Data Index: 726191 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9137. Min Act: -0.1700
Data Index: 3816831 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8512. Min Act: -0.1700
Data Index: 7400095 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8512. Min Act: -0.1700
Data Index: 7459354 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8199. Min Act: -0.1700
Data Index: 6385460 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8199. Min Act: -0.1700
Data Index: 8662517 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8199. Min Act: -0.1700
Data Index: 454358 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7887. Min Act: -0.1700
Data Index: 1200720 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7574. Min Act: -0.1700
Data Index: 6835747 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7574. Min Act: -0.1700
Data Index: 2403438 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7574. Min Act: -0.1700
Data Index: 2374617 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7574. Min Act: -0.1700
Data Index: 5426247 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7574. Min Act: -0.1700
Data Index: 3183157 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7574. Min Act: -0.1700
Data Index: 1519646 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19