Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5607 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.7663. Min Act: -0.1700
Data Index: 1183221 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.7351. Min Act: -0.1700
Data Index: 2834938 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.6413. Min Act: -0.1700
Data Index: 395850 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.6101. Min Act: -0.1700
Data Index: 8048518 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.6101. Min Act: -0.1700
Data Index: 1147018 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.6101. Min Act: -0.1700
Data Index: 1720680 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.6413. Min Act: -0.1700
Data Index: 3006508 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.6101. Min Act: -0.1700
Data Index: 4344667 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.6101. Min Act: -0.1700
Data Index: 4449912 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.6101. Min Act: -0.1700
Data Index: 3399668 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.5476. Min Act: -0.1700
Data Index: 2789201 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.5163. Min Act: -0.1700
Data Index: 7090934 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.5163. Min Act: -0.1700
Data Index: 3107634 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.4851. Min Act: -0.1700
Data Index: 5467696 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.4851. Min Act: -0.1700
Data Index: 7488064 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.4851. Min Act: -0.1700
Data Index: 1576418 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.4538. Min Act: -0.1700
Data Index: 7780067 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.4851. Min Act: -0.1700
Data Index: 2876177 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.4851. Min Act: -0.1700
Data Index: 3910100 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7663. Min Range: -4.7663
Max Act: 4.4851. Min Act: -0.1700
Data Index: 4896380 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19