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

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

Neuron 3853 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: 1.8315. Min Range: -1.8315

Max Act: 1.8315. Min Act: -0.0001

Data Index: 675464 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.8274. Min Act: -0.0001

Data Index: 613336 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.7641. Min Act: -0.0001

Data Index: 796429 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.6995. Min Act: -0.0001

Data Index: 1174518 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.5320. Min Act: -0.0001

Data Index: 407648 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.4945. Min Act: -0.0001

Data Index: 1038624 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.4439. Min Act: -0.0001

Data Index: 884724 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.4127. Min Act: -0.0001

Data Index: 67111 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.4030. Min Act: -0.0001

Data Index: 465931 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.3464. Min Act: -0.0001

Data Index: 579363 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.4275. Min Act: -0.0001

Data Index: 264514 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.3360. Min Act: -0.0001

Data Index: 1288778 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.3327. Min Act: -0.0001

Data Index: 960030 (C4 (Web Text))

Max Activating Token Index: 692

Text #13

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.2803. Min Act: -0.0001

Data Index: 861614 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.2397. Min Act: -0.0001

Data Index: 482180 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.2688. Min Act: -0.0001

Data Index: 1213060 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.2229. Min Act: -0.0001

Data Index: 129529 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.2188. Min Act: -0.0001

Data Index: 525118 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.3390. Min Act: -0.0001

Data Index: 180341 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 1.8315. Min Range: -1.8315

Max Act: 1.2529. Min Act: -0.0001

Data Index: 696366 (C4 (Web Text))

Max Activating Token Index: 156