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

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

Neuron 2564 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: 3.7745. Min Range: -3.7745

Max Act: 3.7745. Min Act: -0.0001

Data Index: 100014 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 3.7745. Min Range: -3.7745

Max Act: 3.1658. Min Act: -0.0001

Data Index: 68186 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.9872. Min Act: -0.0001

Data Index: 1256743 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.4857. Min Act: -0.0001

Data Index: 526831 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.5556. Min Act: -0.0001

Data Index: 664560 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.6640. Min Act: -0.0001

Data Index: 1113386 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.6652. Min Act: -0.0001

Data Index: 206371 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.1438. Min Act: -0.0001

Data Index: 924133 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.4765. Min Act: -0.0001

Data Index: 755580 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.6043. Min Act: -0.0001

Data Index: 424375 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.5518. Min Act: -0.0001

Data Index: 405403 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.3376. Min Act: -0.0001

Data Index: 1334736 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.5437. Min Act: -0.0001

Data Index: 781491 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.4110. Min Act: -0.0000

Data Index: 560278 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.6319. Min Act: -0.0001

Data Index: 1047331 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.6315. Min Act: -0.0001

Data Index: 854099 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.2478. Min Act: -0.0001

Data Index: 957355 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.4919. Min Act: -0.0001

Data Index: 856039 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.5585. Min Act: -0.0001

Data Index: 264465 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 3.7745. Min Range: -3.7745

Max Act: 2.3365. Min Act: -0.0000

Data Index: 343214 (C4 (Web Text))

Max Activating Token Index: 499