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

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

Neuron 3081 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: 1.0355. Min Range: -1.0355

Max Act: 1.0355. Min Act: -0.0000

Data Index: 994249 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.9998. Min Act: -0.0000

Data Index: 471542 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.9331. Min Act: -0.0001

Data Index: 347341 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1303280 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.8746. Min Act: -0.0001

Data Index: 552726 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.8004. Min Act: -0.0000

Data Index: 532600 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7920. Min Act: -0.0001

Data Index: 898660 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.8510. Min Act: -0.0000

Data Index: 586158 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.8464. Min Act: -0.0000

Data Index: 561857 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.8187. Min Act: -0.0001

Data Index: 1028842 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.8185. Min Act: -0.0000

Data Index: 55944 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7996. Min Act: -0.0001

Data Index: 1343834 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7955. Min Act: -0.0001

Data Index: 689813 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7685. Min Act: -0.0000

Data Index: 1077311 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7868. Min Act: -0.0001

Data Index: 1072645 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7795. Min Act: -0.0000

Data Index: 929473 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7576. Min Act: -0.0001

Data Index: 860058 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7542. Min Act: -0.0000

Data Index: 337571 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7532. Min Act: -0.0001

Data Index: 1593 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 1.0355. Min Range: -1.0355

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1284115 (C4 (Web Text))

Max Activating Token Index: 582