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

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

Neuron 654 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1658. Min Range: -2.1658

Max Act: 2.1658. Min Act: -0.0000

Data Index: 404942 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.7266. Min Act: -0.0000

Data Index: 1109707 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5892. Min Act: -0.0000

Data Index: 208496 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5457. Min Act: -0.0000

Data Index: 400710 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.5254. Min Act: -0.0000

Data Index: 702147 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.2647. Min Act: -0.0000

Data Index: 953800 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.2537. Min Act: -0.0000

Data Index: 1321158 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1105016 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.3153. Min Act: -0.0000

Data Index: 125393 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.3221. Min Act: -0.0000

Data Index: 1105765 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.2597. Min Act: -0.0000

Data Index: 762205 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.4044. Min Act: -0.0000

Data Index: 320278 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.1967. Min Act: -0.0000

Data Index: 496483 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.2076. Min Act: -0.0000

Data Index: 916269 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.2104. Min Act: -0.0000

Data Index: 169933 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.1910. Min Act: -0.0000

Data Index: 598724 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.1109. Min Act: -0.0000

Data Index: 1297354 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1135635 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.2012. Min Act: -0.0000

Data Index: 437949 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 2.1658. Min Range: -2.1658

Max Act: 1.1393. Min Act: -0.0000

Data Index: 126511 (C4 (Web Text))

Max Activating Token Index: 534