Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4887 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.5184. Min Act: -0.1700
Data Index: 8605215 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.4559. Min Act: -0.1700
Data Index: 3845032 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.3934. Min Act: -0.1700
Data Index: 5935774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.3621. Min Act: -0.1700
Data Index: 4141622 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.3621. Min Act: -0.1700
Data Index: 142439 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.2996. Min Act: -0.1700
Data Index: 5874803 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.2059. Min Act: -0.1700
Data Index: 5666605 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.1746. Min Act: -0.1700
Data Index: 965586 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.1434. Min Act: -0.1700
Data Index: 2010881 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.1746. Min Act: -0.1700
Data Index: 7019044 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.1434. Min Act: -0.1700
Data Index: 6826234 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.1434. Min Act: -0.1700
Data Index: 2001834 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.0809. Min Act: -0.1700
Data Index: 530510 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.1121. Min Act: -0.1700
Data Index: 7841246 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.1121. Min Act: -0.1700
Data Index: 6280983 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.1121. Min Act: -0.1700
Data Index: 4106434 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.0809. Min Act: -0.1700
Data Index: 2858916 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.0809. Min Act: -0.1700
Data Index: 5912662 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.0496. Min Act: -0.1700
Data Index: 6633601 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5184. Min Range: -5.5184
Max Act: 5.0496. Min Act: -0.1700
Data Index: 3824247 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19