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

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

Neuron 4424 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6545. Min Act: -0.0001

Data Index: 80666 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.7128. Min Act: -0.0001

Data Index: 67336 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6947. Min Act: -0.0001

Data Index: 1110087 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6868. Min Act: -0.0001

Data Index: 750069 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.7355. Min Act: -0.0001

Data Index: 630746 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6396. Min Act: -0.0001

Data Index: 495122 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.7412. Min Act: -0.0001

Data Index: 20269 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6030. Min Act: -0.0001

Data Index: 186098 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5604. Min Act: -0.0001

Data Index: 1194063 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6066. Min Act: -0.0001

Data Index: 339330 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.7340. Min Act: -0.0001

Data Index: 173703 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5866. Min Act: -0.0001

Data Index: 223475 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6645. Min Act: -0.0001

Data Index: 515599 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6339. Min Act: -0.0001

Data Index: 1094226 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5828. Min Act: -0.0001

Data Index: 913170 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.7621. Min Act: -0.0001

Data Index: 513285 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6202. Min Act: -0.0001

Data Index: 739369 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6164. Min Act: -0.0001

Data Index: 1032084 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6337. Min Act: -0.0001

Data Index: 341956 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6344. Min Act: -0.0001

Data Index: 1179827 (C4 (Web Text))

Max Activating Token Index: 968