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

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

Neuron 2660 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: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0003

Data Index: 182045 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1776. Min Act: -0.0003

Data Index: 3891 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1796. Min Act: -0.0003

Data Index: 915237 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1669. Min Act: -0.0003

Data Index: 1138803 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1687. Min Act: -0.0003

Data Index: 1147081 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1660. Min Act: -0.0003

Data Index: 205164 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1505. Min Act: -0.0003

Data Index: 685388 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1569. Min Act: -0.0003

Data Index: 1324552 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1540. Min Act: -0.0003

Data Index: 379757 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1500. Min Act: -0.0003

Data Index: 293971 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1492. Min Act: -0.0003

Data Index: 1351878 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1533. Min Act: -0.0003

Data Index: 1212722 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1576. Min Act: -0.0003

Data Index: 1180089 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1647. Min Act: -0.0003

Data Index: 270723 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1584. Min Act: -0.0003

Data Index: 613843 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1528. Min Act: -0.0003

Data Index: 1143613 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1352. Min Act: -0.0003

Data Index: 145114 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1552. Min Act: -0.0003

Data Index: 1248689 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1489. Min Act: -0.0003

Data Index: 726663 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1533. Min Act: -0.0003

Data Index: 776293 (C4 (Web Text))

Max Activating Token Index: 160