Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 808 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1805. Min Range: -7.1805
Max Act: 7.1805. Min Act: -0.1700
Data Index: 3083690 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1805. Min Range: -7.1805
Max Act: 7.0867. Min Act: -0.1700
Data Index: 4801954 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1805. Min Range: -7.1805
Max Act: 7.0867. Min Act: -0.1700
Data Index: 5121371 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.9617. Min Act: -0.1700
Data Index: 3056343 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.9305. Min Act: -0.1700
Data Index: 1966657 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.8992. Min Act: -0.1700
Data Index: 4911221 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.8992. Min Act: -0.1700
Data Index: 3936587 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.8367. Min Act: -0.1700
Data Index: 2992060 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.8367. Min Act: -0.1700
Data Index: 933782 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.8367. Min Act: -0.1700
Data Index: 4627300 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.7742. Min Act: -0.1700
Data Index: 1057881 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.7117. Min Act: -0.1700
Data Index: 2209286 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.6805. Min Act: -0.1700
Data Index: 7865637 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.6180. Min Act: -0.1700
Data Index: 316998 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.6805. Min Act: -0.1700
Data Index: 432945 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.6805. Min Act: -0.1700
Data Index: 5910410 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.6492. Min Act: -0.1700
Data Index: 6244148 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.6805. Min Act: -0.1700
Data Index: 5436828 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.6492. Min Act: -0.1700
Data Index: 4286636 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1805. Min Range: -7.1805
Max Act: 6.6805. Min Act: -0.1700
Data Index: 1355309 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19