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

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

Neuron 4003 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.3012. Min Act: -0.0001

Data Index: 670786 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1821. Min Act: -0.0001

Data Index: 951010 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.2067. Min Act: -0.0001

Data Index: 80424 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1845. Min Act: -0.0001

Data Index: 1040995 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.2212. Min Act: -0.0001

Data Index: 989936 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1843. Min Act: -0.0001

Data Index: 1225485 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1300. Min Act: -0.0001

Data Index: 814683 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1623. Min Act: -0.0001

Data Index: 314406 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0772. Min Act: -0.0001

Data Index: 195354 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0956. Min Act: -0.0001

Data Index: 149405 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1520. Min Act: -0.0001

Data Index: 221962 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1191. Min Act: -0.0001

Data Index: 473778 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.1351. Min Act: -0.0001

Data Index: 124605 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0433. Min Act: -0.0001

Data Index: 757801 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0965. Min Act: -0.0001

Data Index: 1102661 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0815. Min Act: -0.0001

Data Index: 614613 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.3012. Min Range: -1.3012

Max Act: 0.9776. Min Act: -0.0001

Data Index: 197418 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0515. Min Act: -0.0001

Data Index: 1088729 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.3012. Min Range: -1.3012

Max Act: 1.0338. Min Act: -0.0001

Data Index: 745795 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 1.3012. Min Range: -1.3012

Max Act: 0.9391. Min Act: -0.0001

Data Index: 1095738 (C4 (Web Text))

Max Activating Token Index: 666