Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1512 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.6778. Min Act: -0.0002
Data Index: 1326418 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.8831. Min Act: -0.0002
Data Index: 765515 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0351. Min Range: -2.0351
Max Act: 2.0351. Min Act: -0.0002
Data Index: 400011 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.6132. Min Act: -0.0002
Data Index: 951346 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.9557. Min Act: -0.0002
Data Index: 852820 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.9739. Min Act: -0.0002
Data Index: 291501 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.6602. Min Act: -0.0002
Data Index: 1221826 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.7152. Min Act: -0.0002
Data Index: 621433 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.8695. Min Act: -0.0002
Data Index: 245203 (C4 (Web Text))
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.9747. Min Act: -0.0002
Data Index: 89956 (C4 (Web Text))
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.7722. Min Act: -0.0002
Data Index: 523086 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.8086. Min Act: -0.0002
Data Index: 1220509 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.7155. Min Act: -0.0002
Data Index: 477391 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.7211. Min Act: -0.0002
Data Index: 536318 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.8668. Min Act: -0.0002
Data Index: 79296 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.7247. Min Act: -0.0002
Data Index: 483741 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.5716. Min Act: -0.0002
Data Index: 865455 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.6963. Min Act: -0.0002
Data Index: 534186 (C4 (Web Text))
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.5958. Min Act: -0.0002
Data Index: 1065981 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0351. Min Range: -2.0351
Max Act: 1.4097. Min Act: -0.0002
Data Index: 669242 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19