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

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

Neuron 2369 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1325522 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1884. Min Act: -0.0000

Data Index: 191789 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1889. Min Act: -0.0001

Data Index: 428801 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1281380 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1818. Min Act: -0.0001

Data Index: 638569 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1745. Min Act: -0.0000

Data Index: 55567 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1673. Min Act: -0.0000

Data Index: 401284 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1571. Min Act: -0.0000

Data Index: 211024 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1521. Min Act: -0.0000

Data Index: 801572 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1518. Min Act: -0.0000

Data Index: 744141 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1164711 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1500. Min Act: -0.0000

Data Index: 43105 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1489. Min Act: -0.0001

Data Index: 314568 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1032593 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1473. Min Act: -0.0000

Data Index: 948967 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1533. Min Act: -0.0000

Data Index: 412429 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1447. Min Act: -0.0000

Data Index: 904327 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1490. Min Act: -0.0001

Data Index: 806458 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1406. Min Act: -0.0001

Data Index: 514934 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.2151. Min Range: -0.2151

Max Act: 0.1385. Min Act: -0.0000

Data Index: 620503 (C4 (Web Text))

Max Activating Token Index: 786