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

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

Neuron 3560 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2798. Min Act: -0.0001

Data Index: 134742 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1162039 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2742. Min Act: -0.0001

Data Index: 941556 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2660. Min Act: -0.0001

Data Index: 965674 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2050. Min Act: -0.0001

Data Index: 1202314 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2263. Min Act: -0.0001

Data Index: 710155 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1960. Min Act: -0.0001

Data Index: 831264 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1896. Min Act: -0.0001

Data Index: 21795 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1961. Min Act: -0.0001

Data Index: 252652 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1943. Min Act: -0.0001

Data Index: 1102524 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1221671 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1994. Min Act: -0.0001

Data Index: 9346 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1727. Min Act: -0.0001

Data Index: 522635 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1548. Min Act: -0.0001

Data Index: 1291764 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1299817 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1584. Min Act: -0.0001

Data Index: 508147 (C4 (Web Text))

Max Activating Token Index: 575

Text #16

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1569. Min Act: -0.0001

Data Index: 396080 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1598. Min Act: -0.0001

Data Index: 1040221 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1535. Min Act: -0.0001

Data Index: 1150812 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.1409. Min Act: -0.0001

Data Index: 378003 (C4 (Web Text))

Max Activating Token Index: 720