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

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

Neuron 3508 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.5063. Min Act: -0.0000

Data Index: 196473 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.5199. Min Act: -0.0000

Data Index: 229596 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4851. Min Act: -0.0000

Data Index: 562516 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4441. Min Act: -0.0000

Data Index: 682114 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1226107 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4190. Min Act: -0.0000

Data Index: 841113 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1141701 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4195. Min Act: -0.0000

Data Index: 469594 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3863. Min Act: -0.0000

Data Index: 391517 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3642. Min Act: -0.0000

Data Index: 715326 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1294752 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4128. Min Act: -0.0000

Data Index: 310279 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3676. Min Act: -0.0000

Data Index: 257438 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3430. Min Act: -0.0000

Data Index: 1282159 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.4001. Min Act: -0.0000

Data Index: 109248 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3778. Min Act: -0.0000

Data Index: 900802 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3321. Min Act: -0.0000

Data Index: 742238 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3677. Min Act: -0.0000

Data Index: 993657 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3675. Min Act: -0.0000

Data Index: 688132 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.5199. Min Range: -0.5199

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1070829 (C4 (Web Text))

Max Activating Token Index: 1016