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

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

Neuron 3016 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.5319. Min Act: -0.0001

Data Index: 892452 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1112459 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2802. Min Act: -0.0001

Data Index: 1044433 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2401. Min Act: -0.0001

Data Index: 794343 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2524. Min Act: -0.0001

Data Index: 114745 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2195. Min Act: -0.0001

Data Index: 517171 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2462. Min Act: -0.0001

Data Index: 904664 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2016. Min Act: -0.0001

Data Index: 969862 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2287. Min Act: -0.0001

Data Index: 1347331 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2036. Min Act: -0.0001

Data Index: 116811 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2229. Min Act: -0.0001

Data Index: 541454 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2107. Min Act: -0.0001

Data Index: 962476 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.1959. Min Act: -0.0001

Data Index: 63321 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.1722. Min Act: -0.0001

Data Index: 757234 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.1825. Min Act: -0.0001

Data Index: 551904 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1142447 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.1692. Min Act: -0.0001

Data Index: 616673 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.2021. Min Act: -0.0001

Data Index: 109061 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.1912. Min Act: -0.0001

Data Index: 583915 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 0.5319. Min Range: -0.5319

Max Act: 0.1707. Min Act: -0.0001

Data Index: 776739 (C4 (Web Text))

Max Activating Token Index: 471