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

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

Neuron 1132 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: 1.9684. Min Range: -1.9684

Max Act: 1.9684. Min Act: -0.0001

Data Index: 936643 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.8979. Min Act: -0.0001

Data Index: 862187 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.8672. Min Act: -0.0001

Data Index: 669114 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.8812. Min Act: -0.0001

Data Index: 634120 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.7868. Min Act: -0.0001

Data Index: 532508 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.7286. Min Act: -0.0001

Data Index: 1211030 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.8290. Min Act: -0.0001

Data Index: 98704 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.7155. Min Act: -0.0001

Data Index: 214485 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.8115. Min Act: -0.0000

Data Index: 494311 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.6574. Min Act: -0.0001

Data Index: 492374 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5564. Min Act: -0.0001

Data Index: 714947 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5512. Min Act: -0.0001

Data Index: 33512 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.6298. Min Act: -0.0001

Data Index: 1327029 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.6310. Min Act: -0.0001

Data Index: 61148 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5298. Min Act: -0.0001

Data Index: 997908 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.6032. Min Act: -0.0001

Data Index: 1038559 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5882. Min Act: -0.0001

Data Index: 881406 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.4936. Min Act: -0.0001

Data Index: 916376 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.4806. Min Act: -0.0001

Data Index: 379876 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 1.9684. Min Range: -1.9684

Max Act: 1.5719. Min Act: -0.0001

Data Index: 200043 (C4 (Web Text))

Max Activating Token Index: 131