Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 253 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 6068188 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5116. Min Act: -0.1700
Data Index: 966008 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5116. Min Act: -0.1700
Data Index: 3791198 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4803. Min Act: -0.1700
Data Index: 8437787 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4491. Min Act: -0.1700
Data Index: 6577887 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3866. Min Act: -0.1700
Data Index: 8460747 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3553. Min Act: -0.1700
Data Index: 6011787 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3553. Min Act: -0.1700
Data Index: 6011788 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3553. Min Act: -0.1700
Data Index: 2673900 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3553. Min Act: -0.1700
Data Index: 4052188 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3241. Min Act: -0.1700
Data Index: 737073 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2928. Min Act: -0.1700
Data Index: 4692842 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3241. Min Act: -0.1700
Data Index: 761774 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2928. Min Act: -0.1700
Data Index: 2322520 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2928. Min Act: -0.1700
Data Index: 4494009 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2616. Min Act: -0.1700
Data Index: 295799 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2928. Min Act: -0.1700
Data Index: 5063466 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2303. Min Act: -0.1700
Data Index: 6921702 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2303. Min Act: -0.1700
Data Index: 4285721 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1991. Min Act: -0.1700
Data Index: 680955 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19