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

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

Neuron 5555 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.5651. Min Act: -0.0001

Data Index: 1225167 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.2243. Min Act: -0.0001

Data Index: 601646 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.1267. Min Act: -0.0001

Data Index: 487877 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9665. Min Act: -0.0001

Data Index: 501176 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.0111. Min Act: -0.0001

Data Index: 903382 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.0066. Min Act: -0.0001

Data Index: 1102713 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9622. Min Act: -0.0001

Data Index: 466138 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.0155. Min Act: -0.0001

Data Index: 958902 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.0373. Min Act: -0.0001

Data Index: 102553 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9421. Min Act: -0.0001

Data Index: 216344 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9929. Min Act: -0.0001

Data Index: 21604 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.0156. Min Act: -0.0001

Data Index: 733620 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.8906. Min Act: -0.0001

Data Index: 421173 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9526. Min Act: -0.0001

Data Index: 873664 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.0013. Min Act: -0.0001

Data Index: 144828 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9922. Min Act: -0.0001

Data Index: 1251796 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 1.5651. Min Range: -1.5651

Max Act: 1.0195. Min Act: -0.0001

Data Index: 1321309 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9588. Min Act: -0.0001

Data Index: 669069 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9591. Min Act: -0.0001

Data Index: 147132 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.5651. Min Range: -1.5651

Max Act: 0.9229. Min Act: -0.0001

Data Index: 386694 (C4 (Web Text))

Max Activating Token Index: 765