Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.5832. Min Act: -0.0000

Data Index: 1024718 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.4738. Min Act: -0.0000

Data Index: 321550 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.4112. Min Act: -0.0000

Data Index: 1323784 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1255659 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.3337. Min Act: -0.0000

Data Index: 422295 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.3132. Min Act: -0.0000

Data Index: 1032784 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.3534. Min Act: -0.0000

Data Index: 305488 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.4254. Min Act: -0.0000

Data Index: 538122 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.2464. Min Act: -0.0000

Data Index: 1119383 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.2111. Min Act: -0.0000

Data Index: 654840 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.2764. Min Act: -0.0000

Data Index: 428569 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.2720. Min Act: -0.0000

Data Index: 298013 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1463. Min Act: -0.0000

Data Index: 702127 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.2625. Min Act: -0.0000

Data Index: 35078 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1332. Min Act: -0.0001

Data Index: 95560 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1090433 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.5832. Min Range: -1.5832

Max Act: 0.9991. Min Act: -0.0001

Data Index: 47562 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1009. Min Act: -0.0001

Data Index: 346167 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1657. Min Act: -0.0001

Data Index: 1072888 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1569. Min Act: -0.0000

Data Index: 939719 (C4 (Web Text))

Max Activating Token Index: 1020