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

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

Neuron 749 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1221. Min Range: -3.1221

Max Act: 3.0430. Min Act: -0.0001

Data Index: 746885 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 3.1221. Min Range: -3.1221

Max Act: 3.1221. Min Act: -0.0000

Data Index: 1119331 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.8175. Min Act: -0.0000

Data Index: 546228 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.4704. Min Act: -0.0000

Data Index: 76609 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.6454. Min Act: -0.0001

Data Index: 513646 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.6355. Min Act: -0.0000

Data Index: 469148 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.7191. Min Act: -0.0001

Data Index: 264182 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.4462. Min Act: -0.0001

Data Index: 217138 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.5738. Min Act: -0.0000

Data Index: 1207158 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.3130. Min Act: -0.0001

Data Index: 108461 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.4797. Min Act: -0.0001

Data Index: 1313418 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.4698. Min Act: -0.0000

Data Index: 330969 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.2989. Min Act: -0.0001

Data Index: 990443 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.2973. Min Act: -0.0000

Data Index: 74981 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.2724. Min Act: -0.0000

Data Index: 155961 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.2439. Min Act: -0.0000

Data Index: 153605 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.3693. Min Act: -0.0000

Data Index: 1219972 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.7145. Min Act: -0.0000

Data Index: 1261605 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.5755. Min Act: -0.0001

Data Index: 812866 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 3.1221. Min Range: -3.1221

Max Act: 2.2137. Min Act: -0.0001

Data Index: 443006 (C4 (Web Text))

Max Activating Token Index: 509