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

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

Neuron 4173 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: 1.1658. Min Range: -1.1658

Max Act: 1.1658. Min Act: -0.0000

Data Index: 721709 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0011. Min Act: -0.0000

Data Index: 87811 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0853. Min Act: -0.0000

Data Index: 247021 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0580. Min Act: -0.0000

Data Index: 809458 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0163. Min Act: -0.0000

Data Index: 194704 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1126007 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1195907 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1290242 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 1.1658. Min Range: -1.1658

Max Act: 1.0159. Min Act: -0.0000

Data Index: 904067 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8882. Min Act: -0.0000

Data Index: 342116 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9502. Min Act: -0.0000

Data Index: 546304 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8902. Min Act: -0.0000

Data Index: 340042 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1191754 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1244424 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1090338 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1301425 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1040782 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.7943. Min Act: -0.0000

Data Index: 227410 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.8466. Min Act: -0.0000

Data Index: 974841 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 1.1658. Min Range: -1.1658

Max Act: 0.7393. Min Act: -0.0000

Data Index: 966590 (C4 (Web Text))

Max Activating Token Index: 187