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

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

Neuron 2570 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: 1.4031. Min Range: -1.4031

Max Act: 1.4031. Min Act: -0.0001

Data Index: 131906 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2958. Min Act: -0.0001

Data Index: 1219827 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2656. Min Act: -0.0001

Data Index: 801578 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2154. Min Act: -0.0001

Data Index: 755080 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2304. Min Act: -0.0001

Data Index: 330667 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1794. Min Act: -0.0001

Data Index: 1027089 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1711. Min Act: -0.0001

Data Index: 1117949 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1412. Min Act: -0.0001

Data Index: 756029 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1281. Min Act: -0.0001

Data Index: 1448460 (Python Code)

Max Activating Token Index: 634

Text #9

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1233. Min Act: -0.0001

Data Index: 1307272 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1180. Min Act: -0.0001

Data Index: 1150425 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1178. Min Act: -0.0001

Data Index: 269366 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1126. Min Act: -0.0001

Data Index: 178788 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0974. Min Act: -0.0001

Data Index: 359636 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0883. Min Act: -0.0001

Data Index: 798452 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0893. Min Act: -0.0001

Data Index: 1446982 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0836. Min Act: -0.0001

Data Index: 1604557 (Python Code)

Max Activating Token Index: 970

Text #17

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0809. Min Act: -0.0001

Data Index: 823479 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0826. Min Act: -0.0001

Data Index: 1642093 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0261. Min Act: -0.0001

Data Index: 1241671 (C4 (Web Text))

Max Activating Token Index: 735