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

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

Neuron 3949 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.5339. Min Act: -0.0000

Data Index: 805865 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.5025. Min Act: -0.0000

Data Index: 999703 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.5085. Min Act: -0.0000

Data Index: 444307 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4921. Min Act: -0.0000

Data Index: 88844 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4608. Min Act: -0.0000

Data Index: 721075 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1149237 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4455. Min Act: 0.0000

Data Index: 609853 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4715. Min Act: -0.0000

Data Index: 738777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4555. Min Act: -0.0000

Data Index: 79185 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4478. Min Act: 0.0004

Data Index: 1057891 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4482. Min Act: -0.0000

Data Index: 954724 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4400. Min Act: 0.0000

Data Index: 636867 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4282. Min Act: -0.0000

Data Index: 86739 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1104663 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4518. Min Act: -0.0000

Data Index: 831007 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4489. Min Act: -0.0000

Data Index: 68224 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4591. Min Act: -0.0000

Data Index: 454535 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4187. Min Act: -0.0000

Data Index: 969181 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4299. Min Act: -0.0001

Data Index: 675210 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.5339. Min Range: -0.5339

Max Act: 0.4249. Min Act: -0.0000

Data Index: 715629 (C4 (Web Text))

Max Activating Token Index: 54