Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 640 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1320215 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0399. Min Act: -0.0003

Data Index: 719738 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0364. Min Act: -0.0004

Data Index: 1077376 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1312889 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0352. Min Act: -0.0002

Data Index: 39339 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0364. Min Act: -0.0003

Data Index: 408829 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0340. Min Act: -0.0002

Data Index: 431216 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0347. Min Act: -0.0003

Data Index: 866198 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0346. Min Act: -0.0002

Data Index: 478149 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0353. Min Act: -0.0002

Data Index: 883579 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1347416 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1045607 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0338. Min Act: -0.0003

Data Index: 768143 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1132888 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1131116 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0335. Min Act: -0.0002

Data Index: 1017989 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0328. Min Act: -0.0002

Data Index: 310889 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0347. Min Act: -0.0002

Data Index: 1252694 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0334. Min Act: -0.0002

Data Index: 386196 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0338. Min Act: -0.0003

Data Index: 184926 (C4 (Web Text))

Max Activating Token Index: 582