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

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

Neuron 2372 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: 0.2166. Min Range: -0.2166

Max Act: 0.2166. Min Act: -0.0000

Data Index: 285613 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.2154. Min Act: -0.0000

Data Index: 66068 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1935. Min Act: -0.0000

Data Index: 722032 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1882. Min Act: -0.0000

Data Index: 52497 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1887. Min Act: -0.0000

Data Index: 817222 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1069068 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1204056 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1313493 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1789. Min Act: -0.0000

Data Index: 498091 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1056149 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1644. Min Act: -0.0000

Data Index: 926683 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1673. Min Act: -0.0000

Data Index: 196968 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1670. Min Act: -0.0000

Data Index: 851143 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1717. Min Act: -0.0000

Data Index: 971512 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1214753 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1298024 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1651. Min Act: -0.0000

Data Index: 261781 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1635. Min Act: -0.0000

Data Index: 796018 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1675. Min Act: -0.0000

Data Index: 898242 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.2166. Min Range: -0.2166

Max Act: 0.1612. Min Act: -0.0000

Data Index: 1324549 (C4 (Web Text))

Max Activating Token Index: 421