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

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

Neuron 4540 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: 4.2703. Min Range: -4.2703

Max Act: 4.2703. Min Act: -0.0000

Data Index: 220454 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.0386. Min Act: -0.0000

Data Index: 1020220 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.0269. Min Act: -0.0000

Data Index: 914071 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1632. Min Act: -0.0000

Data Index: 770714 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 4.2703. Min Range: -4.2703

Max Act: 4.1501. Min Act: -0.0000

Data Index: 841691 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.7440. Min Act: -0.0000

Data Index: 873841 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.8770. Min Act: -0.0000

Data Index: 757585 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.6903. Min Act: -0.0000

Data Index: 315302 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.6710. Min Act: -0.0000

Data Index: 1315193 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.8027. Min Act: -0.0000

Data Index: 724482 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.9236. Min Act: -0.0000

Data Index: 618096 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.6283. Min Act: -0.0000

Data Index: 766608 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.7453. Min Act: -0.0000

Data Index: 207462 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.5842. Min Act: -0.0000

Data Index: 242389 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.8913. Min Act: -0.0000

Data Index: 850260 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.5647. Min Act: -0.0000

Data Index: 20732 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.7017. Min Act: -0.0000

Data Index: 669681 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.4192. Min Act: -0.0000

Data Index: 1387414 (Python Code)

Max Activating Token Index: 659

Text #18

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.3071. Min Act: -0.0000

Data Index: 167406 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 4.2703. Min Range: -4.2703

Max Act: 3.4801. Min Act: -0.0000

Data Index: 575064 (C4 (Web Text))

Max Activating Token Index: 257