Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 131 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4588. Min Range: -6.4588
Max Act: 6.4588. Min Act: -0.1700
Data Index: 5880364 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4588. Min Range: -6.4588
Max Act: 6.2088. Min Act: -0.1700
Data Index: 7286351 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4588. Min Range: -6.4588
Max Act: 6.1775. Min Act: -0.1700
Data Index: 8130244 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4588. Min Range: -6.4588
Max Act: 6.1463. Min Act: -0.1700
Data Index: 4310999 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.9900. Min Act: -0.1700
Data Index: 145666 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.9900. Min Act: -0.1700
Data Index: 8766152 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.9900. Min Act: -0.1700
Data Index: 3217339 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.9900. Min Act: -0.1700
Data Index: 7704617 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.9900. Min Act: -0.1700
Data Index: 3018842 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.9275. Min Act: -0.1700
Data Index: 8394301 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.9588. Min Act: -0.1700
Data Index: 7123705 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8963. Min Act: -0.1700
Data Index: 7611049 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8963. Min Act: -0.1700
Data Index: 2138801 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8963. Min Act: -0.1700
Data Index: 7845009 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8338. Min Act: -0.1700
Data Index: 2729894 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8650. Min Act: -0.1700
Data Index: 8584070 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8650. Min Act: -0.1700
Data Index: 4799238 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8338. Min Act: -0.1700
Data Index: 875111 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8338. Min Act: -0.1700
Data Index: 5542804 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4588. Min Range: -6.4588
Max Act: 5.8338. Min Act: -0.1700
Data Index: 6317623 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19