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

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

Neuron 4053 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1551. Min Range: -6.1551

Max Act: 5.9745. Min Act: -0.0000

Data Index: 183549 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 6.1551. Min Range: -6.1551

Max Act: 6.1551. Min Act: -0.0000

Data Index: 420041 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 6.1551. Min Range: -6.1551

Max Act: 5.7469. Min Act: -0.0000

Data Index: 1158433 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 6.1551. Min Range: -6.1551

Max Act: 4.8468. Min Act: -0.0000

Data Index: 320983 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 6.1551. Min Range: -6.1551

Max Act: 5.2919. Min Act: -0.0000

Data Index: 150565 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 6.1551. Min Range: -6.1551

Max Act: 5.5854. Min Act: -0.0000

Data Index: 570610 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 6.1551. Min Range: -6.1551

Max Act: 5.0034. Min Act: -0.0000

Data Index: 23928 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 6.1551. Min Range: -6.1551

Max Act: 5.1511. Min Act: -0.0000

Data Index: 880603 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 6.1551. Min Range: -6.1551

Max Act: 4.6956. Min Act: -0.0000

Data Index: 1329562 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 6.1551. Min Range: -6.1551

Max Act: 4.6213. Min Act: -0.0000

Data Index: 805088 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 6.1551. Min Range: -6.1551

Max Act: 4.8338. Min Act: -0.0000

Data Index: 652600 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 6.1551. Min Range: -6.1551

Max Act: 4.9174. Min Act: -0.0000

Data Index: 878769 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 6.1551. Min Range: -6.1551

Max Act: 3.5290. Min Act: -0.0000

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 6.1551. Min Range: -6.1551

Max Act: 2.9843. Min Act: -0.0000

Data Index: 858113 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 6.1551. Min Range: -6.1551

Max Act: 2.8018. Min Act: -0.0000

Data Index: 1191673 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 6.1551. Min Range: -6.1551

Max Act: 3.0851. Min Act: -0.0000

Data Index: 871695 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 6.1551. Min Range: -6.1551

Max Act: 2.8404. Min Act: -0.0000

Data Index: 123616 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 6.1551. Min Range: -6.1551

Max Act: 2.4031. Min Act: -0.0000

Data Index: 1208126 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 6.1551. Min Range: -6.1551

Max Act: 2.6547. Min Act: -0.0000

Data Index: 342329 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 6.1551. Min Range: -6.1551

Max Act: 2.4609. Min Act: -0.0000

Data Index: 30496 (C4 (Web Text))

Max Activating Token Index: 554