Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.5428. Min Act: -0.1700
Data Index: 5226987 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.5116. Min Act: -0.1700
Data Index: 1864944 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.5116. Min Act: -0.1700
Data Index: 1312434 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.4491. Min Act: -0.1700
Data Index: 8445826 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.4178. Min Act: -0.1700
Data Index: 193444 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3553. Min Act: -0.1700
Data Index: 7715241 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3553. Min Act: -0.1700
Data Index: 7974980 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3866. Min Act: -0.1700
Data Index: 4778443 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3553. Min Act: -0.1700
Data Index: 4094944 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3553. Min Act: -0.1700
Data Index: 7565497 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3553. Min Act: -0.1700
Data Index: 298445 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3553. Min Act: -0.1700
Data Index: 5444189 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3553. Min Act: -0.1700
Data Index: 6387259 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3241. Min Act: -0.1700
Data Index: 4693657 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.3241. Min Act: -0.1700
Data Index: 4155795 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.2928. Min Act: -0.1700
Data Index: 2319755 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.2928. Min Act: -0.1700
Data Index: 6514586 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.2616. Min Act: -0.1700
Data Index: 2363412 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.2616. Min Act: -0.1700
Data Index: 8432522 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5428. Min Range: -6.5428
Max Act: 6.2616. Min Act: -0.1700
Data Index: 3618059 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19