Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 638 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2240. Min Range: -6.2240
Max Act: 6.2240. Min Act: -0.1700
Data Index: 196100 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2240. Min Range: -6.2240
Max Act: 6.0365. Min Act: -0.1700
Data Index: 5435175 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.9115. Min Act: -0.1700
Data Index: 3566668 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.7865. Min Act: -0.1700
Data Index: 7533402 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.7553. Min Act: -0.1700
Data Index: 170825 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.6928. Min Act: -0.1700
Data Index: 7117982 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.7240. Min Act: -0.1700
Data Index: 8594 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.6928. Min Act: -0.1700
Data Index: 1525826 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.6615. Min Act: -0.1700
Data Index: 4713143 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.6615. Min Act: -0.1700
Data Index: 4064749 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.6303. Min Act: -0.1700
Data Index: 6526725 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.6303. Min Act: -0.1700
Data Index: 3343037 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.6303. Min Act: -0.1700
Data Index: 7909126 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.5990. Min Act: -0.1700
Data Index: 8223411 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.5990. Min Act: -0.1700
Data Index: 860079 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.5990. Min Act: -0.1700
Data Index: 5204832 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.5678. Min Act: -0.1700
Data Index: 5169610 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.5990. Min Act: -0.1700
Data Index: 3002108 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.5990. Min Act: -0.1700
Data Index: 2477723 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2240. Min Range: -6.2240
Max Act: 5.5678. Min Act: -0.1700
Data Index: 7413399 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19