Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.9135. Min Act: -0.1700
Data Index: 3271147 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.8510. Min Act: -0.1700
Data Index: 1467082 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.7573. Min Act: -0.1700
Data Index: 1018995 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.5698. Min Act: -0.1700
Data Index: 6789339 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.4135. Min Act: -0.1700
Data Index: 3640874 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.4448. Min Act: -0.1700
Data Index: 3196412 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.3510. Min Act: -0.1700
Data Index: 994458 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.3198. Min Act: -0.1700
Data Index: 3640878 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.3198. Min Act: -0.1700
Data Index: 8459629 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.3198. Min Act: -0.1700
Data Index: 4321042 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.2260. Min Act: -0.1700
Data Index: 7791979 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.2260. Min Act: -0.1700
Data Index: 4389081 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.1635. Min Act: -0.1700
Data Index: 3243890 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.1323. Min Act: -0.1700
Data Index: 7235404 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.1323. Min Act: -0.1700
Data Index: 5722862 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.1323. Min Act: -0.1700
Data Index: 3640876 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.1323. Min Act: -0.1700
Data Index: 253237 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.1010. Min Act: -0.1700
Data Index: 2230315 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.1010. Min Act: -0.1700
Data Index: 7487130 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9135. Min Range: -6.9135
Max Act: 6.1010. Min Act: -0.1700
Data Index: 97422 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19