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

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

Neuron 2783 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3733. Min Range: -1.3733

Max Act: 1.3733. Min Act: -0.0000

Data Index: 666589 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.9140. Min Act: -0.0000

Data Index: 1149536 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.8888. Min Act: -0.0001

Data Index: 1119018 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.8553. Min Act: -0.0001

Data Index: 664807 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1254362 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.8003. Min Act: -0.0000

Data Index: 30475 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.8269. Min Act: -0.0000

Data Index: 363716 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7685. Min Act: -0.0001

Data Index: 21105 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7354. Min Act: -0.0001

Data Index: 811168 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1278333 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.8004. Min Act: -0.0001

Data Index: 1246828 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7500. Min Act: -0.0001

Data Index: 355301 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.8499. Min Act: -0.0001

Data Index: 544618 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7985. Min Act: -0.0001

Data Index: 1054174 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7662. Min Act: -0.0001

Data Index: 200951 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7613. Min Act: -0.0001

Data Index: 767272 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7459. Min Act: -0.0000

Data Index: 240762 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7041. Min Act: -0.0001

Data Index: 484697 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7282. Min Act: -0.0001

Data Index: 555192 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 1.3733. Min Range: -1.3733

Max Act: 0.7163. Min Act: -0.0001

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 700