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

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

Neuron 3256 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5727. Min Range: -2.5727

Max Act: 2.5727. Min Act: -0.0000

Data Index: 1462782 (Python Code)

Max Activating Token Index: 990

Text #1

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.5746. Min Act: 0.0000

Data Index: 394260 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.6627. Min Act: -0.0000

Data Index: 891079 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.5759. Min Act: -0.0000

Data Index: 1079362 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.4765. Min Act: -0.0000

Data Index: 495126 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.4035. Min Act: 0.0000

Data Index: 1193087 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.2723. Min Act: -0.0000

Data Index: 235451 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.4556. Min Act: -0.0000

Data Index: 1153464 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.1339. Min Act: 0.0000

Data Index: 172247 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.3085. Min Act: -0.0000

Data Index: 713018 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.2213. Min Act: 0.0000

Data Index: 435894 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.2507. Min Act: 0.0000

Data Index: 1332723 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.2548. Min Act: -0.0000

Data Index: 128183 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.2709. Min Act: -0.0000

Data Index: 339790 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1140553 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.1638. Min Act: 0.0000

Data Index: 1179037 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.3086. Min Act: 0.0000

Data Index: 1258254 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.2217. Min Act: 0.0000

Data Index: 1347947 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.2484. Min Act: -0.0000

Data Index: 295316 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 2.5727. Min Range: -2.5727

Max Act: 1.1798. Min Act: -0.0000

Data Index: 786021 (C4 (Web Text))

Max Activating Token Index: 669