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

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

Neuron 2608 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: 0.5284. Min Range: -0.5284

Max Act: 0.5284. Min Act: -0.0000

Data Index: 55187 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1106962 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1120418 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4482. Min Act: -0.0000

Data Index: 144736 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4480. Min Act: -0.0000

Data Index: 855283 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4443. Min Act: -0.0000

Data Index: 666934 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4215. Min Act: -0.0000

Data Index: 957850 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4246. Min Act: -0.0000

Data Index: 996279 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4253. Min Act: -0.0000

Data Index: 613600 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4173. Min Act: -0.0000

Data Index: 731602 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4159. Min Act: -0.0000

Data Index: 647660 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1143552 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.4131. Min Act: -0.0000

Data Index: 683996 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1056043 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3814. Min Act: -0.0000

Data Index: 791581 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3823. Min Act: -0.0000

Data Index: 539305 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3689. Min Act: -0.0000

Data Index: 83581 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3616. Min Act: -0.0000

Data Index: 915793 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3574. Min Act: -0.0000

Data Index: 735664 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.5284. Min Range: -0.5284

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1132787 (C4 (Web Text))

Max Activating Token Index: 241