Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.7240. Min Act: -0.1700
Data Index: 1429707 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.6928. Min Act: -0.1700
Data Index: 2587531 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.6928. Min Act: -0.1700
Data Index: 8362006 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.6303. Min Act: -0.1700
Data Index: 5400090 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5990. Min Act: -0.1700
Data Index: 2752953 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5990. Min Act: -0.1700
Data Index: 7326692 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5990. Min Act: -0.1700
Data Index: 7411342 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5678. Min Act: -0.1700
Data Index: 1196322 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5678. Min Act: -0.1700
Data Index: 7765573 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5678. Min Act: -0.1700
Data Index: 8813368 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5678. Min Act: -0.1699
Data Index: 5196867 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5678. Min Act: -0.1700
Data Index: 6068302 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5678. Min Act: -0.1697
Data Index: 7116476 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5365. Min Act: -0.1698
Data Index: 2587530 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5365. Min Act: -0.1700
Data Index: 2528975 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5365. Min Act: -0.1700
Data Index: 6572437 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5365. Min Act: -0.1700
Data Index: 5142197 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5365. Min Act: -0.1700
Data Index: 4831833 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5365. Min Act: -0.1700
Data Index: 3674462 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7240. Min Range: -4.7240
Max Act: 4.5365. Min Act: -0.1700
Data Index: 3369448 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19