Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.3425. Min Act: -0.0001

Data Index: 288675 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2962. Min Act: -0.0002

Data Index: 376677 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2783. Min Act: -0.0002

Data Index: 537847 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2624. Min Act: -0.0001

Data Index: 990628 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2637. Min Act: -0.0001

Data Index: 800903 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1213916 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2411. Min Act: -0.0001

Data Index: 657468 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2175. Min Act: -0.0002

Data Index: 424063 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2377. Min Act: -0.0002

Data Index: 731797 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2491. Min Act: -0.0002

Data Index: 423616 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2121. Min Act: -0.0002

Data Index: 178460 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2096. Min Act: -0.0001

Data Index: 9917 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2221. Min Act: -0.0001

Data Index: 722619 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2243. Min Act: -0.0001

Data Index: 205486 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2005. Min Act: -0.0002

Data Index: 507639 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2158. Min Act: -0.0002

Data Index: 892641 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2189. Min Act: -0.0002

Data Index: 475707 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2409. Min Act: -0.0002

Data Index: 929407 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.1894. Min Act: -0.0002

Data Index: 539343 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.3425. Min Range: -0.3425

Max Act: 0.2093. Min Act: -0.0002

Data Index: 815728 (C4 (Web Text))

Max Activating Token Index: 546