Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 38 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.5760. Min Act: -0.0000

Data Index: 672374 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.5185. Min Act: -0.0000

Data Index: 950473 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.5359. Min Act: -0.0000

Data Index: 133774 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.5072. Min Act: -0.0000

Data Index: 64253 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.5035. Min Act: -0.0000

Data Index: 353934 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1485501 (Python Code)

Max Activating Token Index: 437

Text #6

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4767. Min Act: -0.0000

Data Index: 844952 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.5284. Min Act: -0.0000

Data Index: 483185 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1069027 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4574. Min Act: -0.0000

Data Index: 2878 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1326385 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4431. Min Act: -0.0000

Data Index: 490506 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1351124 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4779. Min Act: -0.0000

Data Index: 793245 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1332634 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4190. Min Act: -0.0000

Data Index: 344556 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4177. Min Act: -0.0000

Data Index: 103568 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.3907. Min Act: -0.0000

Data Index: 1004487 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4168. Min Act: -0.0000

Data Index: 469701 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.5760. Min Range: -0.5760

Max Act: 0.4419. Min Act: -0.0000

Data Index: 264596 (C4 (Web Text))

Max Activating Token Index: 12