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

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

Neuron 4818 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0156. Min Act: -0.0000

Data Index: 754126 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.1132. Min Act: -0.0000

Data Index: 397055 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0732. Min Act: -0.0000

Data Index: 575962 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0715. Min Act: -0.0000

Data Index: 572989 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0735. Min Act: -0.0000

Data Index: 128108 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1311956 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0671. Min Act: -0.0000

Data Index: 627396 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0620. Min Act: -0.0000

Data Index: 219187 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0700. Min Act: -0.0000

Data Index: 949366 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0678. Min Act: -0.0000

Data Index: 606392 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0702. Min Act: -0.0000

Data Index: 678119 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1216375 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1045546 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0603. Min Act: -0.0000

Data Index: 787788 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0622. Min Act: -0.0000

Data Index: 1170314 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0620. Min Act: -0.0000

Data Index: 107956 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0588. Min Act: -0.0000

Data Index: 355936 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0575. Min Act: -0.0000

Data Index: 945836 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0557. Min Act: -0.0000

Data Index: 29440 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.1132. Min Range: -0.1132

Max Act: 0.0620. Min Act: -0.0000

Data Index: 406193 (C4 (Web Text))

Max Activating Token Index: 223