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

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

Neuron 854 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2486. Min Act: -0.0002

Data Index: 1272671 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2141. Min Act: -0.0002

Data Index: 277298 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1864. Min Act: -0.0002

Data Index: 83429 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1827. Min Act: -0.0002

Data Index: 1223451 (C4 (Web Text))

Max Activating Token Index: 176

Text #4

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1767. Min Act: -0.0002

Data Index: 1357448 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1577. Min Act: -0.0002

Data Index: 1162673 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1484. Min Act: -0.0002

Data Index: 617840 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1778. Min Act: -0.0002

Data Index: 412933 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1890. Min Act: -0.0002

Data Index: 480333 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1622. Min Act: -0.0002

Data Index: 971493 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1577. Min Act: -0.0002

Data Index: 451 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1571. Min Act: -0.0002

Data Index: 606163 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1614. Min Act: -0.0002

Data Index: 485993 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1500. Min Act: -0.0002

Data Index: 332228 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1623. Min Act: -0.0002

Data Index: 832924 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1555. Min Act: -0.0002

Data Index: 1327195 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1633. Min Act: -0.0002

Data Index: 219722 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1555. Min Act: -0.0002

Data Index: 1035697 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1626. Min Act: -0.0002

Data Index: 200223 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1556. Min Act: -0.0002

Data Index: 142364 (C4 (Web Text))

Max Activating Token Index: 281