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

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

Neuron 2171 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8703. Min Act: -0.0000

Data Index: 950071 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8643. Min Act: 0.0000

Data Index: 756802 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1194076 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1001270 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7468. Min Act: -0.0000

Data Index: 342517 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7725. Min Act: -0.0001

Data Index: 1181694 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7654. Min Act: -0.0001

Data Index: 656043 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7202. Min Act: -0.0000

Data Index: 730131 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1202495 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7230. Min Act: -0.0000

Data Index: 600491 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7372. Min Act: -0.0000

Data Index: 8132 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6940. Min Act: -0.0001

Data Index: 954017 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7314. Min Act: -0.0000

Data Index: 774608 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7019. Min Act: -0.0000

Data Index: 223769 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6650. Min Act: -0.0000

Data Index: 121497 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6865. Min Act: -0.0001

Data Index: 300255 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6763. Min Act: -0.0000

Data Index: 614388 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7032. Min Act: -0.0001

Data Index: 1119581 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6621. Min Act: -0.0000

Data Index: 860986 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6529. Min Act: -0.0000

Data Index: 561896 (C4 (Web Text))

Max Activating Token Index: 91