Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 188 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5366. Min Range: -1.5366

Max Act: 1.5366. Min Act: -0.0000

Data Index: 659412 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.5366. Min Range: -1.5366

Max Act: 1.0360. Min Act: -0.0000

Data Index: 18658 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 1.5366. Min Range: -1.5366

Max Act: 1.0740. Min Act: -0.0001

Data Index: 172279 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 1.5366. Min Range: -1.5366

Max Act: 1.0012. Min Act: -0.0001

Data Index: 291441 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.9148. Min Act: -0.0000

Data Index: 330659 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.9398. Min Act: -0.0001

Data Index: 765971 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.9638. Min Act: -0.0001

Data Index: 2393 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.9202. Min Act: -0.0001

Data Index: 505865 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.9197. Min Act: -0.0000

Data Index: 257594 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.8962. Min Act: -0.0001

Data Index: 981779 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.9052. Min Act: -0.0000

Data Index: 438880 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.9034. Min Act: -0.0001

Data Index: 1152828 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.9249. Min Act: -0.0001

Data Index: 317915 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.8617. Min Act: -0.0001

Data Index: 1113297 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.8882. Min Act: -0.0000

Data Index: 545458 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.8304. Min Act: -0.0001

Data Index: 218699 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.8357. Min Act: -0.0000

Data Index: 727177 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.8583. Min Act: -0.0001

Data Index: 1303374 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.8214. Min Act: -0.0001

Data Index: 563210 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 1.5366. Min Range: -1.5366

Max Act: 0.8608. Min Act: -0.0001

Data Index: 995481 (C4 (Web Text))

Max Activating Token Index: 415