Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.2371. Min Act: -0.1700
Data Index: 3923078 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.2058. Min Act: -0.1700
Data Index: 207994 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.1746. Min Act: -0.1700
Data Index: 4537531 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.1433. Min Act: -0.1700
Data Index: 3855129 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0496. Min Act: -0.1700
Data Index: 3658485 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0496. Min Act: -0.1700
Data Index: 3178897 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0496. Min Act: -0.1700
Data Index: 7282971 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0496. Min Act: -0.1700
Data Index: 8100007 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0496. Min Act: -0.1700
Data Index: 8600760 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0183. Min Act: -0.1700
Data Index: 2716386 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0183. Min Act: -0.1700
Data Index: 5950371 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0183. Min Act: -0.1700
Data Index: 4108928 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0183. Min Act: -0.1700
Data Index: 8829243 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0183. Min Act: -0.1700
Data Index: 7389161 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0183. Min Act: -0.1700
Data Index: 8681616 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0496. Min Act: -0.1700
Data Index: 1405050 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2371. Min Range: -4.2371
Max Act: 4.0183. Min Act: -0.1700
Data Index: 5983825 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2371. Min Range: -4.2371
Max Act: 3.9870. Min Act: -0.1700
Data Index: 4266756 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2371. Min Range: -4.2371
Max Act: 3.9870. Min Act: -0.1700
Data Index: 8531372 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2371. Min Range: -4.2371
Max Act: 3.9870. Min Act: -0.1700
Data Index: 3128947 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19