Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4187 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.9043. Min Act: -0.1700
Data Index: 3953317 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8787. Min Act: -0.1700
Data Index: 1377362 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8787. Min Act: -0.1700
Data Index: 4677743 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8616. Min Act: -0.1700
Data Index: 7134333 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8616. Min Act: -0.1700
Data Index: 8578471 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8530. Min Act: -0.1700
Data Index: 4792399 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8530. Min Act: -0.1699
Data Index: 1841444 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8359. Min Act: -0.1700
Data Index: 8595905 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8445. Min Act: -0.1700
Data Index: 4246422 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8359. Min Act: -0.1698
Data Index: 5745397 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8445. Min Act: -0.1700
Data Index: 3136512 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8273. Min Act: -0.1700
Data Index: 5207242 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8273. Min Act: -0.1700
Data Index: 6193466 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8273. Min Act: -0.1700
Data Index: 5392081 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8187. Min Act: -0.1700
Data Index: 3501334 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8273. Min Act: -0.1700
Data Index: 2676831 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8187. Min Act: -0.1700
Data Index: 5183249 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8187. Min Act: -0.1700
Data Index: 280389 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8187. Min Act: -0.1700
Data Index: 5099931 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9043. Min Range: -1.9043
Max Act: 1.8273. Min Act: -0.1700
Data Index: 5980929 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19