Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.5006. Min Act: -0.1700
Data Index: 698524 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.3131. Min Act: -0.1700
Data Index: 5886194 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.3131. Min Act: -0.1700
Data Index: 1396713 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.3131. Min Act: -0.1700
Data Index: 989728 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.2506. Min Act: -0.1700
Data Index: 7241892 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.2506. Min Act: -0.1700
Data Index: 4311803 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.1881. Min Act: -0.1700
Data Index: 8753086 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.1881. Min Act: -0.1700
Data Index: 5147432 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0631. Min Act: -0.1700
Data Index: 4422507 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.1881. Min Act: -0.1700
Data Index: 3793014 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.1256. Min Act: -0.1700
Data Index: 8060119 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0631. Min Act: -0.1700
Data Index: 1609977 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0631. Min Act: -0.1700
Data Index: 1191537 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0631. Min Act: -0.1700
Data Index: 839855 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0006. Min Act: -0.1700
Data Index: 8632407 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0006. Min Act: -0.1700
Data Index: 1836510 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0006. Min Act: -0.1700
Data Index: 6137160 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0006. Min Act: -0.1700
Data Index: 7427398 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0006. Min Act: -0.1700
Data Index: 3824361 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5006. Min Range: -8.5006
Max Act: 8.0006. Min Act: -0.1700
Data Index: 8778116 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19