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

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

Neuron 2224 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.2337. Min Act: -0.0001

Data Index: 71121 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.4318. Min Act: -0.0000

Data Index: 987642 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.2182. Min Act: -0.0000

Data Index: 1024598 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.1733. Min Act: -0.0001

Data Index: 1113568 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.1421. Min Act: -0.0001

Data Index: 430468 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.1310. Min Act: -0.0000

Data Index: 532692 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.0866. Min Act: -0.0000

Data Index: 918824 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.0815. Min Act: -0.0001

Data Index: 326845 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.0490. Min Act: -0.0000

Data Index: 79271 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.1397. Min Act: -0.0001

Data Index: 1011708 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 2.4318. Min Range: -2.4318

Max Act: 1.8350. Min Act: -0.0001

Data Index: 880163 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.0417. Min Act: -0.0000

Data Index: 590435 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.0026. Min Act: -0.0000

Data Index: 724236 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 2.4318. Min Range: -2.4318

Max Act: 1.9902. Min Act: -0.0000

Data Index: 835035 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 2.4318. Min Range: -2.4318

Max Act: 1.6932. Min Act: -0.0000

Data Index: 241566 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 2.4318. Min Range: -2.4318

Max Act: 1.8569. Min Act: -0.0001

Data Index: 420683 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 2.4318. Min Range: -2.4318

Max Act: 1.8630. Min Act: -0.0001

Data Index: 433519 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 2.4318. Min Range: -2.4318

Max Act: 1.9442. Min Act: -0.0001

Data Index: 971353 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 2.4318. Min Range: -2.4318

Max Act: 1.8392. Min Act: -0.0001

Data Index: 383619 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 2.4318. Min Range: -2.4318

Max Act: 2.0040. Min Act: -0.0000

Data Index: 1242209 (C4 (Web Text))

Max Activating Token Index: 879