Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 828 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.1063. Min Act: -0.0001

Data Index: 800647 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0639. Min Act: -0.0001

Data Index: 417267 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9891. Min Act: -0.0001

Data Index: 1017732 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0006. Min Act: -0.0001

Data Index: 1353344 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9594. Min Act: -0.0001

Data Index: 1025838 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 1.1063. Min Range: -1.1063

Max Act: 1.0134. Min Act: -0.0001

Data Index: 776098 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.8151. Min Act: -0.0001

Data Index: 1358233 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9471. Min Act: -0.0001

Data Index: 219580 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9255. Min Act: -0.0001

Data Index: 301950 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9194. Min Act: -0.0001

Data Index: 209826 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9475. Min Act: -0.0001

Data Index: 1262749 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9408. Min Act: -0.0001

Data Index: 590572 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9159. Min Act: -0.0001

Data Index: 1141650 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.9053. Min Act: -0.0001

Data Index: 838637 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.8189. Min Act: -0.0001

Data Index: 144154 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.8936. Min Act: -0.0001

Data Index: 832051 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.8414. Min Act: -0.0001

Data Index: 880800 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.8414. Min Act: -0.0001

Data Index: 109555 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.8677. Min Act: -0.0001

Data Index: 698332 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 1.1063. Min Range: -1.1063

Max Act: 0.8639. Min Act: -0.0001

Data Index: 843382 (C4 (Web Text))

Max Activating Token Index: 701