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

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

Neuron 526 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.8389. Min Act: -0.0001

Data Index: 743893 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.8522. Min Act: -0.0001

Data Index: 773941 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.3893. Min Act: -0.0001

Data Index: 875632 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.5210. Min Act: -0.0001

Data Index: 439893 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.5424. Min Act: -0.0001

Data Index: 203197 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.6738. Min Act: -0.0001

Data Index: 1050631 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.4102. Min Act: -0.0001

Data Index: 506762 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.5649. Min Act: -0.0001

Data Index: 198190 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2722. Min Act: -0.0001

Data Index: 432201 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.3796. Min Act: -0.0001

Data Index: 458542 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.3187. Min Act: -0.0001

Data Index: 121420 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.3257. Min Act: -0.0001

Data Index: 289261 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.3920. Min Act: -0.0001

Data Index: 1179366 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2006. Min Act: -0.0001

Data Index: 577558 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2613. Min Act: -0.0001

Data Index: 1125361 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2206. Min Act: -0.0001

Data Index: 456698 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2856. Min Act: -0.0001

Data Index: 957195 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2152. Min Act: -0.0001

Data Index: 172282 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2903. Min Act: -0.0001

Data Index: 1153318 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 1.8522. Min Range: -1.8522

Max Act: 1.2863. Min Act: -0.0001

Data Index: 893360 (C4 (Web Text))

Max Activating Token Index: 464