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

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

Neuron 3531 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: 0.1836. Min Range: -0.1836

Max Act: 0.1582. Min Act: -0.0001

Data Index: 183685 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1836. Min Act: -0.0001

Data Index: 857496 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1576. Min Act: -0.0001

Data Index: 383927 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1345731 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1543. Min Act: -0.0001

Data Index: 1223526 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1212. Min Act: -0.0001

Data Index: 770049 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1406. Min Act: -0.0001

Data Index: 871877 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1419. Min Act: -0.0001

Data Index: 753381 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1588. Min Act: -0.0001

Data Index: 834393 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1526. Min Act: -0.0001

Data Index: 112307 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1435. Min Act: -0.0001

Data Index: 96422 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1439. Min Act: -0.0001

Data Index: 441882 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1393. Min Act: -0.0001

Data Index: 843054 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1439. Min Act: -0.0001

Data Index: 633168 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1313. Min Act: -0.0001

Data Index: 371420 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1388. Min Act: -0.0001

Data Index: 49947 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1230. Min Act: -0.0001

Data Index: 37950 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1261. Min Act: -0.0001

Data Index: 333092 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1213. Min Act: -0.0001

Data Index: 153313 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.1836. Min Range: -0.1836

Max Act: 0.1170. Min Act: -0.0001

Data Index: 447879 (C4 (Web Text))

Max Activating Token Index: 674