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

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

Neuron 5113 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.7511. Min Act: -0.0000

Data Index: 1270271 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.8347. Min Act: -0.0000

Data Index: 614142 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.5719. Min Act: -0.0000

Data Index: 919124 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.5365. Min Act: -0.0000

Data Index: 540986 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.4334. Min Act: -0.0000

Data Index: 45604 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.4166. Min Act: -0.0000

Data Index: 47450 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.4189. Min Act: -0.0000

Data Index: 375533 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.4018. Min Act: -0.0000

Data Index: 1277961 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.4487. Min Act: -0.0000

Data Index: 449500 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.2938. Min Act: -0.0000

Data Index: 233245 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1096582 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.1848. Min Act: -0.0000

Data Index: 474950 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.1937. Min Act: -0.0000

Data Index: 80907 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.3333. Min Act: -0.0000

Data Index: 836695 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1107079 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.2369. Min Act: -0.0000

Data Index: 1164671 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.2174. Min Act: -0.0000

Data Index: 723454 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1234722 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.2821. Min Act: -0.0000

Data Index: 1028060 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 1.8347. Min Range: -1.8347

Max Act: 1.2807. Min Act: -0.0000

Data Index: 492900 (C4 (Web Text))

Max Activating Token Index: 461