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

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

Neuron 824 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: 5.4037. Min Range: -5.4037

Max Act: 5.4037. Min Act: -0.0000

Data Index: 1347 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 5.4037. Min Range: -5.4037

Max Act: 5.1143. Min Act: -0.0000

Data Index: 354115 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.6298. Min Act: -0.0000

Data Index: 420925 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 5.4037. Min Range: -5.4037

Max Act: 4.1058. Min Act: -0.0000

Data Index: 259051 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.9506. Min Act: -0.0000

Data Index: 1038855 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.4246. Min Act: -0.0000

Data Index: 146365 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.8607. Min Act: -0.0000

Data Index: 946715 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.7854. Min Act: -0.0000

Data Index: 559804 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.5799. Min Act: -0.0000

Data Index: 1014219 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.6421. Min Act: -0.0000

Data Index: 923783 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.4741. Min Act: -0.0000

Data Index: 309862 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.4164. Min Act: -0.0000

Data Index: 54380 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.2247. Min Act: -0.0000

Data Index: 1027825 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.3564. Min Act: -0.0000

Data Index: 414257 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.4734. Min Act: -0.0000

Data Index: 801919 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.2847. Min Act: -0.0000

Data Index: 432651 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.2728. Min Act: -0.0000

Data Index: 217598 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.2673. Min Act: -0.0000

Data Index: 230812 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.2701. Min Act: -0.0000

Data Index: 947821 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 5.4037. Min Range: -5.4037

Max Act: 3.2324. Min Act: -0.0000

Data Index: 963825 (C4 (Web Text))

Max Activating Token Index: 327