Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 27 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0752. Min Range: -5.0752
Max Act: 5.0752. Min Act: -0.1700
Data Index: 7632379 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0752. Min Range: -5.0752
Max Act: 5.0752. Min Act: -0.1700
Data Index: 2888688 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0752. Min Range: -5.0752
Max Act: 5.0439. Min Act: -0.1700
Data Index: 340160 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0752. Min Range: -5.0752
Max Act: 5.0439. Min Act: -0.1700
Data Index: 6200762 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.9814. Min Act: -0.1700
Data Index: 4488404 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.9502. Min Act: -0.1700
Data Index: 8454023 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.9502. Min Act: -0.1700
Data Index: 6724796 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.9502. Min Act: -0.1700
Data Index: 7122270 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.9502. Min Act: -0.1700
Data Index: 5086847 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.9189. Min Act: -0.1700
Data Index: 4747678 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8877. Min Act: -0.1700
Data Index: 8727075 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8877. Min Act: -0.1700
Data Index: 3573433 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8564. Min Act: -0.1700
Data Index: 8544925 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8877. Min Act: -0.1700
Data Index: 241414 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8564. Min Act: -0.1700
Data Index: 1314260 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8877. Min Act: -0.1700
Data Index: 7019910 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8877. Min Act: -0.1700
Data Index: 4103246 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8877. Min Act: -0.1700
Data Index: 5795758 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8252. Min Act: -0.1700
Data Index: 246535 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0752. Min Range: -5.0752
Max Act: 4.8564. Min Act: -0.1700
Data Index: 1578893 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19