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

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

Neuron 4866 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.6204. Min Act: -0.0002

Data Index: 240964 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.6806. Min Act: -0.0002

Data Index: 288498 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.6328. Min Act: -0.0002

Data Index: 1327729 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5311. Min Act: -0.0002

Data Index: 1230752 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.4519. Min Act: -0.0002

Data Index: 246335 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2176. Min Act: -0.0002

Data Index: 363528 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2423. Min Act: -0.0002

Data Index: 1092595 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.1762. Min Act: -0.0002

Data Index: 785631 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2266. Min Act: -0.0002

Data Index: 1066046 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2344. Min Act: -0.0002

Data Index: 145807 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.5133. Min Act: -0.0002

Data Index: 7834 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2446. Min Act: -0.0002

Data Index: 665433 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.3306. Min Act: -0.0002

Data Index: 1210279 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2287. Min Act: -0.0002

Data Index: 443830 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.1495. Min Act: -0.0002

Data Index: 682242 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.1716. Min Act: -0.0002

Data Index: 1238132 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2882. Min Act: -0.0002

Data Index: 520751 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.3410. Min Act: -0.0002

Data Index: 337315 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.1882. Min Act: -0.0002

Data Index: 1296055 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.1494. Min Act: -0.0002

Data Index: 868894 (C4 (Web Text))

Max Activating Token Index: 726