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

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

Neuron 4535 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3658. Min Range: -2.3658

Max Act: 2.3658. Min Act: -0.0000

Data Index: 446452 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 2.3658. Min Range: -2.3658

Max Act: 2.3384. Min Act: -0.0000

Data Index: 891191 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 2.3658. Min Range: -2.3658

Max Act: 2.2112. Min Act: -0.0000

Data Index: 1359346 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 2.3658. Min Range: -2.3658

Max Act: 2.1785. Min Act: -0.0000

Data Index: 442390 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 2.3658. Min Range: -2.3658

Max Act: 2.0619. Min Act: -0.0000

Data Index: 126910 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 2.3658. Min Range: -2.3658

Max Act: 2.2508. Min Act: -0.0000

Data Index: 309754 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 2.3658. Min Range: -2.3658

Max Act: 2.0786. Min Act: -0.0000

Data Index: 914248 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 2.3658. Min Range: -2.3658

Max Act: 2.1190. Min Act: -0.0000

Data Index: 43428 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.9608. Min Act: -0.0000

Data Index: 107037 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.9615. Min Act: -0.0000

Data Index: 567932 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.9369. Min Act: -0.0000

Data Index: 1159816 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.7656. Min Act: -0.0000

Data Index: 217356 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.8593. Min Act: -0.0000

Data Index: 307577 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.9635. Min Act: -0.0000

Data Index: 466950 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.8438. Min Act: -0.0000

Data Index: 314548 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.8277. Min Act: -0.0000

Data Index: 724865 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.8323. Min Act: -0.0000

Data Index: 625394 (C4 (Web Text))

Max Activating Token Index: 416

Text #17

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.7252. Min Act: -0.0000

Data Index: 270178 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.8247. Min Act: -0.0000

Data Index: 562645 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 2.3658. Min Range: -2.3658

Max Act: 1.9231. Min Act: -0.0000

Data Index: 309127 (C4 (Web Text))

Max Activating Token Index: 749