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

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

Neuron 2485 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1879. Min Act: -0.0000

Data Index: 690090 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1696. Min Act: -0.0000

Data Index: 134054 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1679. Min Act: -0.0000

Data Index: 784047 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1623. Min Act: -0.0000

Data Index: 144575 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1472. Min Act: -0.0000

Data Index: 577354 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1483. Min Act: -0.0000

Data Index: 161703 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1472. Min Act: -0.0000

Data Index: 549188 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1375. Min Act: -0.0000

Data Index: 116063 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1153772 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1327. Min Act: -0.0000

Data Index: 659120 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1295. Min Act: -0.0000

Data Index: 580888 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1406. Min Act: -0.0000

Data Index: 132936 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1294. Min Act: -0.0000

Data Index: 755319 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1427. Min Act: -0.0000

Data Index: 173108 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1279682 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1229. Min Act: -0.0000

Data Index: 472795 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1223. Min Act: -0.0000

Data Index: 457576 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1233. Min Act: -0.0000

Data Index: 710618 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1232. Min Act: -0.0000

Data Index: 497683 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1220446 (C4 (Web Text))

Max Activating Token Index: 854