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

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

Neuron 2192 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4862. Min Act: -0.0000

Data Index: 435555 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4464. Min Act: -0.0001

Data Index: 1026912 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4556. Min Act: -0.0001

Data Index: 546861 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4684. Min Act: -0.0001

Data Index: 1501652 (Python Code)

Max Activating Token Index: 255

Text #4

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4332. Min Act: -0.0000

Data Index: 556250 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4429. Min Act: -0.0001

Data Index: 832324 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4300. Min Act: -0.0000

Data Index: 506797 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4195. Min Act: -0.0000

Data Index: 330244 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4367. Min Act: -0.0001

Data Index: 750325 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4346. Min Act: -0.0001

Data Index: 182284 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4453. Min Act: -0.0001

Data Index: 109023 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4286. Min Act: -0.0001

Data Index: 1335538 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4359. Min Act: -0.0001

Data Index: 455683 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4334. Min Act: -0.0001

Data Index: 638859 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4169. Min Act: -0.0000

Data Index: 250231 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4301. Min Act: -0.0000

Data Index: 728027 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4252. Min Act: -0.0000

Data Index: 515612 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4194. Min Act: -0.0001

Data Index: 162701 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.4176. Min Act: -0.0001

Data Index: 1287744 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.4862. Min Range: -0.4862

Max Act: 0.3731. Min Act: -0.0001

Data Index: 1068197 (C4 (Web Text))

Max Activating Token Index: 791