Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4625 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.4584. Min Act: -0.0000

Data Index: 284470 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.5616. Min Act: -0.0000

Data Index: 794609 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.4632. Min Act: -0.0000

Data Index: 1118437 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.1753. Min Act: -0.0000

Data Index: 886152 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.0216. Min Act: -0.0000

Data Index: 279102 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.0725. Min Act: -0.0000

Data Index: 534878 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.5446. Min Act: -0.0000

Data Index: 525478 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.0319. Min Act: -0.0000

Data Index: 1281164 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.9394. Min Act: -0.0000

Data Index: 1161798 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.1019. Min Act: -0.0000

Data Index: 1329918 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.8708. Min Act: -0.0000

Data Index: 270962 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.8623. Min Act: -0.0000

Data Index: 303861 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.8524. Min Act: -0.0000

Data Index: 45425 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.8923. Min Act: -0.0000

Data Index: 464138 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 2.5616. Min Range: -2.5616

Max Act: 2.0001. Min Act: -0.0000

Data Index: 745699 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.8600. Min Act: -0.0000

Data Index: 1180632 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.8209. Min Act: -0.0000

Data Index: 951333 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.9393. Min Act: -0.0000

Data Index: 625626 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.8482. Min Act: -0.0000

Data Index: 1214546 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 2.5616. Min Range: -2.5616

Max Act: 1.8501. Min Act: -0.0000

Data Index: 305555 (C4 (Web Text))

Max Activating Token Index: 978