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

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

Neuron 53 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.2110. Min Act: -0.0001

Data Index: 618165 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1697. Min Act: -0.0001

Data Index: 247043 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1794. Min Act: -0.0000

Data Index: 180636 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1609. Min Act: -0.0000

Data Index: 121836 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1656. Min Act: -0.0000

Data Index: 666518 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1601. Min Act: -0.0001

Data Index: 607877 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1114457 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1587. Min Act: -0.0001

Data Index: 339089 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1628. Min Act: -0.0001

Data Index: 478208 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1186697 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1206981 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1448. Min Act: -0.0001

Data Index: 814600 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1005276 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1478. Min Act: -0.0000

Data Index: 157616 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1396. Min Act: -0.0000

Data Index: 937208 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1325. Min Act: -0.0000

Data Index: 981248 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1327. Min Act: -0.0001

Data Index: 747715 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1359. Min Act: -0.0000

Data Index: 233154 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1136194 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.2110. Min Range: -0.2110

Max Act: 0.1432. Min Act: -0.0000

Data Index: 332507 (C4 (Web Text))

Max Activating Token Index: 677