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

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

Neuron 2441 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: 0.6927. Min Range: -0.6927

Max Act: 0.6397. Min Act: -0.0000

Data Index: 727917 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6703. Min Act: -0.0000

Data Index: 567708 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6927. Min Act: -0.0000

Data Index: 625045 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6321. Min Act: 0.0000

Data Index: 916852 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5726. Min Act: -0.0000

Data Index: 963267 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6318. Min Act: -0.0000

Data Index: 699475 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1061805 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1303571 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1338230 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5647. Min Act: -0.0000

Data Index: 926214 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5550. Min Act: -0.0000

Data Index: 879814 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5766. Min Act: 0.0001

Data Index: 1302220 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5386. Min Act: -0.0000

Data Index: 761988 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5197. Min Act: -0.0000

Data Index: 126896 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5042. Min Act: -0.0000

Data Index: 924475 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5019. Min Act: -0.0000

Data Index: 606642 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5234. Min Act: -0.0000

Data Index: 899285 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.4612. Min Act: -0.0000

Data Index: 308387 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.4628. Min Act: -0.0000

Data Index: 955731 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.4513. Min Act: -0.0000

Data Index: 560309 (C4 (Web Text))

Max Activating Token Index: 999