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

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

Neuron 1522 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0150. Min Range: -3.0150

Max Act: 3.0150. Min Act: -0.0000

Data Index: 812447 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.8642. Min Act: -0.0000

Data Index: 1000011 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.6339. Min Act: -0.0000

Data Index: 407691 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.5303. Min Act: -0.0000

Data Index: 431076 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.6553. Min Act: 0.0001

Data Index: 889888 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.3065. Min Act: -0.0000

Data Index: 398294 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.5156. Min Act: -0.0000

Data Index: 1062658 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.5115. Min Act: -0.0000

Data Index: 350593 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.3421. Min Act: -0.0000

Data Index: 125410 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.4853. Min Act: -0.0000

Data Index: 837172 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.3255. Min Act: -0.0000

Data Index: 662826 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.2778. Min Act: -0.0000

Data Index: 493138 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.2611. Min Act: -0.0000

Data Index: 47286 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.1402. Min Act: -0.0000

Data Index: 931325 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.3536. Min Act: -0.0000

Data Index: 267279 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.3221. Min Act: -0.0000

Data Index: 304606 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.1564. Min Act: -0.0000

Data Index: 865191 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.2480. Min Act: -0.0000

Data Index: 800815 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 3.0150. Min Range: -3.0150

Max Act: 2.2034. Min Act: -0.0000

Data Index: 160158 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 3.0150. Min Range: -3.0150

Max Act: 1.9828. Min Act: -0.0000

Data Index: 1213061 (C4 (Web Text))

Max Activating Token Index: 720