Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 370 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.3400. Min Act: -0.0003

Data Index: 365923 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2478. Min Act: -0.0003

Data Index: 515700 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2039. Min Act: -0.0003

Data Index: 212838 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.2238. Min Act: -0.0003

Data Index: 919539 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1637. Min Act: -0.0003

Data Index: 1225409 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1413. Min Act: -0.0003

Data Index: 76895 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1481. Min Act: -0.0003

Data Index: 593476 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1666. Min Act: -0.0003

Data Index: 6020 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1421. Min Act: -0.0003

Data Index: 852390 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1356. Min Act: -0.0003

Data Index: 52231 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1453. Min Act: -0.0003

Data Index: 252815 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1541. Min Act: -0.0003

Data Index: 1245416 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1591. Min Act: -0.0003

Data Index: 960626 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1574. Min Act: -0.0003

Data Index: 977504 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1461. Min Act: -0.0003

Data Index: 789641 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1409. Min Act: -0.0003

Data Index: 994886 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1501. Min Act: -0.0003

Data Index: 807739 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1210. Min Act: -0.0003

Data Index: 1252727 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1316488 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.3400. Min Range: -0.3400

Max Act: 0.1356. Min Act: -0.0003

Data Index: 1128214 (C4 (Web Text))

Max Activating Token Index: 638