Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3656 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0495. Min Act: -0.0001

Data Index: 1271560 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0479. Min Act: -0.0001

Data Index: 1054683 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0487. Min Act: -0.0001

Data Index: 993240 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0000

Data Index: 169785 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0483. Min Act: -0.0001

Data Index: 103746 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0485. Min Act: -0.0000

Data Index: 748406 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0483. Min Act: -0.0000

Data Index: 236720 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0479. Min Act: -0.0001

Data Index: 171611 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0433. Min Act: -0.0000

Data Index: 198117 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0446. Min Act: -0.0000

Data Index: 687461 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0416. Min Act: -0.0001

Data Index: 446729 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0492. Min Act: -0.0000

Data Index: 247915 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0453. Min Act: -0.0000

Data Index: 36903 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0436. Min Act: -0.0000

Data Index: 202660 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1007728 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1263638 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0442. Min Act: -0.0001

Data Index: 1133472 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0425. Min Act: -0.0001

Data Index: 436660 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1099749 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0422. Min Act: -0.0000

Data Index: 187235 (C4 (Web Text))

Max Activating Token Index: 569