Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5173 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1117. Min Range: -5.1117
Max Act: 5.1117. Min Act: -0.1700
Data Index: 352721 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1117. Min Range: -5.1117
Max Act: 5.1117. Min Act: -0.1700
Data Index: 2728292 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.9867. Min Act: -0.1700
Data Index: 8084113 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.9242. Min Act: -0.1700
Data Index: 622378 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.8929. Min Act: -0.1700
Data Index: 1411028 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.8304. Min Act: -0.1700
Data Index: 1581932 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7679. Min Act: -0.1700
Data Index: 3282994 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7992. Min Act: -0.1700
Data Index: 5633143 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7992. Min Act: -0.1700
Data Index: 2977666 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7679. Min Act: -0.1700
Data Index: 3569504 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7992. Min Act: -0.1700
Data Index: 1206599 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7367. Min Act: -0.1700
Data Index: 866061 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7367. Min Act: -0.1700
Data Index: 2977665 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7367. Min Act: -0.1700
Data Index: 4825885 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7054. Min Act: -0.1700
Data Index: 8095000 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.7054. Min Act: -0.1700
Data Index: 3302367 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.6742. Min Act: -0.1700
Data Index: 2477662 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.6742. Min Act: -0.1700
Data Index: 5556007 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.6117. Min Act: -0.1700
Data Index: 7572264 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1117. Min Range: -5.1117
Max Act: 4.6117. Min Act: -0.1700
Data Index: 235731 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19