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

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

Neuron 2029 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0003

Data Index: 434428 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0341. Min Act: -0.0003

Data Index: 879170 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0321. Min Act: -0.0003

Data Index: 690901 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0310. Min Act: -0.0003

Data Index: 547038 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0313. Min Act: -0.0003

Data Index: 699425 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0315. Min Act: -0.0004

Data Index: 147011 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0296. Min Act: -0.0003

Data Index: 669265 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0312. Min Act: -0.0003

Data Index: 420371 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0285. Min Act: -0.0003

Data Index: 409259 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1218173 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0286. Min Act: -0.0004

Data Index: 107200 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0263. Min Act: -0.0003

Data Index: 826343 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0288. Min Act: -0.0003

Data Index: 767874 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0273. Min Act: -0.0003

Data Index: 164745 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1339239 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0278. Min Act: -0.0003

Data Index: 509335 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1088505 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1118915 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1037352 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0270. Min Act: -0.0003

Data Index: 64138 (C4 (Web Text))

Max Activating Token Index: 123