Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3004 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4196. Min Range: -4.4196
Max Act: 4.4196. Min Act: -0.1700
Data Index: 5385849 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4196. Min Range: -4.4196
Max Act: 4.2321. Min Act: -0.1700
Data Index: 3020492 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4196. Min Range: -4.4196
Max Act: 4.0133. Min Act: -0.1700
Data Index: 4916239 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4196. Min Range: -4.4196
Max Act: 4.0133. Min Act: -0.1700
Data Index: 4339101 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.9820. Min Act: -0.1700
Data Index: 5107559 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.9508. Min Act: -0.1700
Data Index: 5767469 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.9508. Min Act: -0.1700
Data Index: 3261147 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.9508. Min Act: -0.1700
Data Index: 4186730 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.9195. Min Act: -0.1700
Data Index: 1430617 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.9195. Min Act: -0.1700
Data Index: 8282633 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8883. Min Act: -0.1700
Data Index: 6136761 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8570. Min Act: -0.1700
Data Index: 7948739 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8570. Min Act: -0.1700
Data Index: 4157827 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8257. Min Act: -0.1700
Data Index: 4487345 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8570. Min Act: -0.1700
Data Index: 5882300 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8257. Min Act: -0.1700
Data Index: 7744548 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8257. Min Act: -0.1700
Data Index: 4155983 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8257. Min Act: -0.1700
Data Index: 5137848 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8257. Min Act: -0.1700
Data Index: 6995364 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4196. Min Range: -4.4196
Max Act: 3.8257. Min Act: -0.1700
Data Index: 743634 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19