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

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

Neuron 1762 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0002

Data Index: 252554 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1165839 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0554. Min Act: -0.0002

Data Index: 480020 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0560. Min Act: -0.0002

Data Index: 15463 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1348399 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0567. Min Act: -0.0002

Data Index: 370617 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0503. Min Act: -0.0002

Data Index: 473234 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0425. Min Act: -0.0002

Data Index: 517975 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0519. Min Act: -0.0002

Data Index: 770228 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0492. Min Act: -0.0002

Data Index: 517209 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0475. Min Act: -0.0002

Data Index: 802755 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1141788 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0456. Min Act: -0.0002

Data Index: 352059 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1264308 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1103234 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0469. Min Act: -0.0002

Data Index: 840272 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0419. Min Act: -0.0002

Data Index: 587813 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0427. Min Act: -0.0002

Data Index: 24012 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1224325 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0439. Min Act: -0.0002

Data Index: 638752 (C4 (Web Text))

Max Activating Token Index: 912