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

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

Neuron 4286 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.6320. Min Act: -0.0000

Data Index: 656057 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.4753. Min Act: -0.0000

Data Index: 1297857 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.3315. Min Act: -0.0000

Data Index: 1013777 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.2137. Min Act: -0.0000

Data Index: 269815 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.1452. Min Act: -0.0000

Data Index: 838618 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.1562. Min Act: -0.0000

Data Index: 1257035 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.9501. Min Act: -0.0000

Data Index: 1242673 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.3232. Min Act: -0.0000

Data Index: 481018 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.0257. Min Act: -0.0000

Data Index: 1101636 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 2.6320. Min Range: -2.6320

Max Act: 2.0515. Min Act: -0.0000

Data Index: 270721 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.9928. Min Act: -0.0000

Data Index: 1314930 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.8713. Min Act: -0.0000

Data Index: 308333 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.8208. Min Act: -0.0000

Data Index: 632310 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.7943. Min Act: -0.0000

Data Index: 586503 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.8000. Min Act: -0.0000

Data Index: 441556 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.7380. Min Act: -0.0000

Data Index: 1200238 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.6671. Min Act: -0.0000

Data Index: 682731 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.9043. Min Act: -0.0000

Data Index: 1096296 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.7279. Min Act: -0.0000

Data Index: 850919 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 2.6320. Min Range: -2.6320

Max Act: 1.8639. Min Act: -0.0000

Data Index: 706889 (C4 (Web Text))

Max Activating Token Index: 492