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

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

Neuron 2023 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: 1.1789. Min Range: -1.1789

Max Act: 1.1789. Min Act: -0.0000

Data Index: 172329 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.1789. Min Range: -1.1789

Max Act: 1.1692. Min Act: -0.0000

Data Index: 111376 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.9471. Min Act: -0.0000

Data Index: 975661 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1091162 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8644. Min Act: -0.0000

Data Index: 957431 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1217239 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1308813 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7625. Min Act: -0.0000

Data Index: 856735 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7658. Min Act: -0.0000

Data Index: 607753 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1091203 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7223. Min Act: -0.0000

Data Index: 546723 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7344. Min Act: -0.0000

Data Index: 235887 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7586. Min Act: -0.0000

Data Index: 487301 (C4 (Web Text))

Max Activating Token Index: 746

Text #13

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7332. Min Act: -0.0000

Data Index: 447432 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7247. Min Act: -0.0000

Data Index: 906378 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7251. Min Act: -0.0000

Data Index: 299751 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7238. Min Act: -0.0000

Data Index: 765226 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7193. Min Act: -0.0000

Data Index: 560845 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7156. Min Act: -0.0000

Data Index: 669372 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.6883. Min Act: -0.0000

Data Index: 18602 (C4 (Web Text))

Max Activating Token Index: 1017