Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1720 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.8587. Min Act: -0.1700
Data Index: 4810874 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.8274. Min Act: -0.1700
Data Index: 8013766 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.8274. Min Act: -0.1700
Data Index: 4972450 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.7649. Min Act: -0.1700
Data Index: 1677510 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.7336. Min Act: -0.1700
Data Index: 178700 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.7180. Min Act: -0.1700
Data Index: 1644723 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.7180. Min Act: -0.1700
Data Index: 8375584 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6867. Min Act: -0.1700
Data Index: 4562574 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6867. Min Act: -0.1700
Data Index: 3452647 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6554. Min Act: -0.1700
Data Index: 6065671 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6554. Min Act: -0.1700
Data Index: 1339071 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6554. Min Act: -0.1700
Data Index: 7146168 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6554. Min Act: -0.1700
Data Index: 4519777 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6554. Min Act: -0.1700
Data Index: 1765944 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6241. Min Act: -0.1700
Data Index: 4164843 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6397. Min Act: -0.1700
Data Index: 1015609 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6397. Min Act: -0.1700
Data Index: 1560614 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6241. Min Act: -0.1700
Data Index: 1709620 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6397. Min Act: -0.1700
Data Index: 5096935 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8587. Min Range: -3.8587
Max Act: 3.6241. Min Act: -0.1700
Data Index: 8228653 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19