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

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

Neuron 3383 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: 0.9539. Min Range: -0.9539

Max Act: 0.9539. Min Act: -0.0001

Data Index: 281744 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.9518. Min Act: -0.0001

Data Index: 507337 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.8328. Min Act: -0.0001

Data Index: 556927 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7487. Min Act: -0.0001

Data Index: 668790 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7530. Min Act: -0.0001

Data Index: 1138869 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7621. Min Act: -0.0001

Data Index: 304418 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6854. Min Act: -0.0001

Data Index: 1255143 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7308. Min Act: -0.0001

Data Index: 87213 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6353. Min Act: -0.0001

Data Index: 21241 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7164. Min Act: -0.0001

Data Index: 1032662 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6914. Min Act: -0.0001

Data Index: 588129 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6820. Min Act: -0.0001

Data Index: 247709 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1150792 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7034. Min Act: -0.0001

Data Index: 92239 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7043. Min Act: -0.0001

Data Index: 965493 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.7146. Min Act: -0.0001

Data Index: 111246 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6423. Min Act: -0.0001

Data Index: 584753 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6658. Min Act: -0.0001

Data Index: 27734 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6435. Min Act: -0.0001

Data Index: 604451 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.9539. Min Range: -0.9539

Max Act: 0.6862. Min Act: -0.0001

Data Index: 1299928 (C4 (Web Text))

Max Activating Token Index: 449