Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1737 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1246. Min Range: -7.1246
Max Act: 7.1246. Min Act: -0.1700
Data Index: 3035994 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1246. Min Range: -7.1246
Max Act: 7.1246. Min Act: -0.1700
Data Index: 8192932 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1246. Min Range: -7.1246
Max Act: 7.0309. Min Act: -0.1700
Data Index: 3331992 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.9371. Min Act: -0.1700
Data Index: 5654213 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.8434. Min Act: -0.1700
Data Index: 1296597 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7496. Min Act: -0.1700
Data Index: 4186608 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7809. Min Act: -0.1700
Data Index: 6982635 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7809. Min Act: -0.1700
Data Index: 472659 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7184. Min Act: -0.1700
Data Index: 883139 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7496. Min Act: -0.1700
Data Index: 5281716 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7496. Min Act: -0.1700
Data Index: 949441 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7496. Min Act: -0.1700
Data Index: 6290967 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7184. Min Act: -0.1700
Data Index: 8619759 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7184. Min Act: -0.1700
Data Index: 4590969 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.6871. Min Act: -0.1700
Data Index: 5705856 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7184. Min Act: -0.1700
Data Index: 3541836 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.6871. Min Act: -0.1700
Data Index: 7171268 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.6871. Min Act: -0.1700
Data Index: 5566431 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.7184. Min Act: -0.1700
Data Index: 6577782 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1246. Min Range: -7.1246
Max Act: 6.6871. Min Act: -0.1700
Data Index: 7693192 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19