Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.0252. Min Range: -10.0252
Max Act: 10.0252. Min Act: -0.1700
Data Index: 2267421 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.4627. Min Act: -0.1700
Data Index: 464607 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.4002. Min Act: -0.1700
Data Index: 6090535 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.4002. Min Act: -0.1700
Data Index: 8282873 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.3377. Min Act: -0.1700
Data Index: 6809881 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.2752. Min Act: -0.1700
Data Index: 6809882 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.2752. Min Act: -0.1700
Data Index: 6294463 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.2127. Min Act: -0.1700
Data Index: 8116579 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.2127. Min Act: -0.1700
Data Index: 7914140 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.2752. Min Act: -0.1700
Data Index: 8539679 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.1502. Min Act: -0.1700
Data Index: 6978656 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.2127. Min Act: -0.1700
Data Index: 5228049 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.2127. Min Act: -0.1700
Data Index: 8314016 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.1502. Min Act: -0.1700
Data Index: 6809868 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.1502. Min Act: -0.1700
Data Index: 6809884 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.0877. Min Act: -0.1700
Data Index: 5223499 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.1502. Min Act: -0.1700
Data Index: 4122304 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.0877. Min Act: -0.1700
Data Index: 4176552 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.0877. Min Act: -0.1700
Data Index: 6978662 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.0252. Min Act: -0.1700
Data Index: 3773471 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19