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

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

Neuron 318 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0003

Data Index: 842817 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1210028 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0310. Min Act: -0.0003

Data Index: 784615 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0313. Min Act: -0.0002

Data Index: 798184 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0313. Min Act: -0.0003

Data Index: 257202 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1349910 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0283. Min Act: -0.0003

Data Index: 681574 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0282. Min Act: -0.0003

Data Index: 377195 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0284. Min Act: -0.0002

Data Index: 935983 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1248925 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1356742 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0276. Min Act: -0.0002

Data Index: 165037 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1248787 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0270. Min Act: -0.0003

Data Index: 46495 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0273. Min Act: -0.0003

Data Index: 121674 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0277. Min Act: -0.0002

Data Index: 678399 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0269. Min Act: -0.0003

Data Index: 649565 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0266. Min Act: -0.0003

Data Index: 153215 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0264. Min Act: -0.0003

Data Index: 190537 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0267. Min Act: -0.0003

Data Index: 970087 (C4 (Web Text))

Max Activating Token Index: 629