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

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

Neuron 1138 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: 1.7325. Min Range: -1.7325

Max Act: 1.6387. Min Act: -0.0001

Data Index: 574340 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.7325. Min Act: -0.0000

Data Index: 1040379 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.6656. Min Act: -0.0001

Data Index: 570007 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.6205. Min Act: -0.0001

Data Index: 914756 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.5770. Min Act: -0.0000

Data Index: 982482 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4400. Min Act: -0.0001

Data Index: 1231980 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4273. Min Act: -0.0001

Data Index: 893195 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4748. Min Act: -0.0001

Data Index: 1344788 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4418. Min Act: -0.0001

Data Index: 1283187 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4002. Min Act: -0.0001

Data Index: 92810 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4363. Min Act: -0.0001

Data Index: 256227 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.4063. Min Act: -0.0001

Data Index: 676459 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3978. Min Act: -0.0001

Data Index: 1089921 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3931. Min Act: -0.0001

Data Index: 1209268 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3621. Min Act: -0.0000

Data Index: 370414 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3191. Min Act: -0.0001

Data Index: 691847 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3345. Min Act: -0.0001

Data Index: 785297 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3649. Min Act: -0.0001

Data Index: 1131242 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.3095. Min Act: -0.0001

Data Index: 929850 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 1.7325. Min Range: -1.7325

Max Act: 1.2986. Min Act: -0.0001

Data Index: 654837 (C4 (Web Text))

Max Activating Token Index: 522