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

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

Neuron 5588 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5448. Min Act: -0.0001

Data Index: 852963 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4702. Min Act: -0.0001

Data Index: 1106877 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5287. Min Act: -0.0001

Data Index: 2593 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1287188 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5213. Min Act: -0.0001

Data Index: 266688 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.5531. Min Act: -0.0001

Data Index: 560660 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4537. Min Act: -0.0001

Data Index: 606648 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4492. Min Act: -0.0000

Data Index: 648962 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4157. Min Act: -0.0000

Data Index: 100835 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4182. Min Act: -0.0001

Data Index: 168269 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4079. Min Act: -0.0000

Data Index: 369530 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4439. Min Act: -0.0001

Data Index: 1086227 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3779. Min Act: -0.0001

Data Index: 497826 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3654. Min Act: -0.0001

Data Index: 147558 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1016040 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3967. Min Act: -0.0000

Data Index: 38435 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1090904 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3866. Min Act: -0.0000

Data Index: 158582 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.4062. Min Act: -0.0000

Data Index: 187522 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.5531. Min Range: -0.5531

Max Act: 0.3789. Min Act: -0.0001

Data Index: 406922 (C4 (Web Text))

Max Activating Token Index: 977