Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 129 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0571. Min Act: -0.0003

Data Index: 134471 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1152416 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0322. Min Act: -0.0003

Data Index: 235453 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0322. Min Act: -0.0003

Data Index: 972185 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0329. Min Act: -0.0003

Data Index: 84288 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0305. Min Act: -0.0003

Data Index: 105977 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0331. Min Act: -0.0003

Data Index: 283709 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1194172 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0312. Min Act: -0.0003

Data Index: 348560 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0298. Min Act: -0.0003

Data Index: 197105 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1011804 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0270. Min Act: -0.0003

Data Index: 442029 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0307. Min Act: -0.0003

Data Index: 476061 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0322. Min Act: -0.0003

Data Index: 227800 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0283. Min Act: -0.0003

Data Index: 969350 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1290295 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0271. Min Act: -0.0003

Data Index: 652960 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0289. Min Act: -0.0003

Data Index: 508706 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0282. Min Act: -0.0003

Data Index: 811952 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1332102 (C4 (Web Text))

Max Activating Token Index: 636