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

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

Neuron 4044 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1265. Min Act: -0.0001

Data Index: 102815 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0979. Min Act: -0.0001

Data Index: 808522 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0647. Min Act: -0.0001

Data Index: 919846 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1257507 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0679. Min Act: -0.0001

Data Index: 238981 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0633. Min Act: -0.0001

Data Index: 93153 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0559. Min Act: -0.0001

Data Index: 1243615 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0582. Min Act: -0.0001

Data Index: 326701 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0566. Min Act: -0.0001

Data Index: 931579 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0511. Min Act: -0.0001

Data Index: 825928 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0492. Min Act: -0.0001

Data Index: 529374 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1075342 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1346880 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0505. Min Act: -0.0001

Data Index: 161778 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0483. Min Act: -0.0001

Data Index: 591778 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0496. Min Act: -0.0001

Data Index: 125948 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1319278 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0481. Min Act: -0.0001

Data Index: 121110 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1145406 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0433. Min Act: -0.0001

Data Index: 187661 (C4 (Web Text))

Max Activating Token Index: 425