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

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

Neuron 824 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2352. Min Range: -2.2352

Max Act: 2.2352. Min Act: -0.0000

Data Index: 19128 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 2.2352. Min Range: -2.2352

Max Act: 2.2125. Min Act: -0.0000

Data Index: 49618 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 2.2352. Min Range: -2.2352

Max Act: 2.2066. Min Act: -0.0000

Data Index: 511226 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 2.2352. Min Range: -2.2352

Max Act: 2.1823. Min Act: -0.0000

Data Index: 1332291 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 2.2352. Min Range: -2.2352

Max Act: 2.0375. Min Act: -0.0000

Data Index: 1225881 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.9609. Min Act: -0.0000

Data Index: 771565 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 2.2352. Min Range: -2.2352

Max Act: 2.0119. Min Act: -0.0000

Data Index: 1268542 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.9027. Min Act: -0.0000

Data Index: 252658 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 2.2352. Min Range: -2.2352

Max Act: 2.0985. Min Act: -0.0000

Data Index: 913565 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.8266. Min Act: -0.0000

Data Index: 641996 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.8992. Min Act: -0.0000

Data Index: 1017522 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.7296. Min Act: -0.0000

Data Index: 567182 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.7316. Min Act: -0.0000

Data Index: 1230971 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.7129. Min Act: -0.0000

Data Index: 918488 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.5974. Min Act: -0.0000

Data Index: 728231 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.6746. Min Act: -0.0000

Data Index: 710542 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.7710. Min Act: -0.0000

Data Index: 523881 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.6641. Min Act: -0.0000

Data Index: 784489 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.6484. Min Act: -0.0001

Data Index: 1021885 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 2.2352. Min Range: -2.2352

Max Act: 1.5328. Min Act: -0.0000

Data Index: 1187341 (C4 (Web Text))

Max Activating Token Index: 215