Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 853 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0260. Min Range: -2.0260

Max Act: 2.0260. Min Act: -0.0000

Data Index: 1285649 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.8084. Min Act: -0.0000

Data Index: 130486 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.7569. Min Act: -0.0000

Data Index: 260360 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.8371. Min Act: -0.0000

Data Index: 95577 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.6995. Min Act: -0.0000

Data Index: 513521 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.6420. Min Act: -0.0000

Data Index: 188766 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.6316. Min Act: -0.0000

Data Index: 551559 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.6300. Min Act: -0.0000

Data Index: 1216079 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.4549. Min Act: -0.0000

Data Index: 694196 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.3895. Min Act: -0.0000

Data Index: 1315885 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.3710. Min Act: -0.0000

Data Index: 1054266 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.4642. Min Act: -0.0000

Data Index: 136900 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.5484. Min Act: -0.0000

Data Index: 166089 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.2985. Min Act: -0.0000

Data Index: 340320 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.3536. Min Act: -0.0000

Data Index: 1061015 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.4343. Min Act: -0.0000

Data Index: 1336000 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.2879. Min Act: -0.0000

Data Index: 1321227 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.3674. Min Act: -0.0000

Data Index: 792120 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.1939. Min Act: -0.0000

Data Index: 641167 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 2.0260. Min Range: -2.0260

Max Act: 1.2557. Min Act: -0.0000

Data Index: 5686 (C4 (Web Text))

Max Activating Token Index: 590