Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4311 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.4375. Min Act: -0.0000

Data Index: 502050 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.4135. Min Act: -0.0000

Data Index: 256866 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.3627. Min Act: -0.0000

Data Index: 759936 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.1687. Min Act: -0.0000

Data Index: 552647 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2092. Min Act: -0.0000

Data Index: 803830 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2562. Min Act: -0.0000

Data Index: 51020 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.2245. Min Act: -0.0000

Data Index: 565476 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.0785. Min Act: -0.0000

Data Index: 126605 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.0200. Min Act: -0.0000

Data Index: 864175 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.4375. Min Range: -1.4375

Max Act: 1.0248. Min Act: -0.0000

Data Index: 466216 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.9260. Min Act: -0.0000

Data Index: 836879 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1117892 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.9760. Min Act: -0.0000

Data Index: 454166 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.9706. Min Act: -0.0000

Data Index: 951700 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.9759. Min Act: -0.0000

Data Index: 994255 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1119161 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.8380. Min Act: -0.0000

Data Index: 662915 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.8742. Min Act: -0.0000

Data Index: 641118 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.9340. Min Act: -0.0000

Data Index: 422074 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.4375. Min Range: -1.4375

Max Act: 0.8640. Min Act: -0.0000

Data Index: 722441 (C4 (Web Text))

Max Activating Token Index: 600