Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 452 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.7486. Min Act: -0.1700
Data Index: 7300050 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.4986. Min Act: -0.1700
Data Index: 5830908 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.4361. Min Act: -0.1700
Data Index: 8803125 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.4361. Min Act: -0.1700
Data Index: 6336383 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.3736. Min Act: -0.1700
Data Index: 2576284 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.4986. Min Act: -0.1700
Data Index: 7185214 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.2486. Min Act: -0.1700
Data Index: 116447 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.3111. Min Act: -0.1700
Data Index: 935954 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1236. Min Act: -0.1700
Data Index: 4705713 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1861. Min Act: -0.1700
Data Index: 8103636 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.2486. Min Act: -0.1700
Data Index: 4392732 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1236. Min Act: -0.1700
Data Index: 5394010 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1861. Min Act: -0.1700
Data Index: 4061922 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.0611. Min Act: -0.1700
Data Index: 4575213 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1236. Min Act: -0.1700
Data Index: 452390 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1236. Min Act: -0.1700
Data Index: 7831890 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1236. Min Act: -0.1700
Data Index: 1135355 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1236. Min Act: -0.1700
Data Index: 3357239 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.0611. Min Act: -0.1700
Data Index: 7305651 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7486. Min Range: -9.7486
Max Act: 9.1236. Min Act: -0.1700
Data Index: 2780328 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19