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

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

Neuron 4153 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.8363. Min Act: -0.0001

Data Index: 423148 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.7093. Min Act: -0.0001

Data Index: 1329893 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5697. Min Act: -0.0000

Data Index: 889623 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5352. Min Act: -0.0001

Data Index: 11132 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5373. Min Act: -0.0001

Data Index: 1230875 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5347. Min Act: -0.0001

Data Index: 1099499 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4806. Min Act: -0.0000

Data Index: 607055 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4907. Min Act: -0.0001

Data Index: 304170 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.5397. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4677. Min Act: -0.0000

Data Index: 810796 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4522. Min Act: -0.0001

Data Index: 378938 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1191747 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1008723 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4534. Min Act: -0.0001

Data Index: 1296950 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4272. Min Act: -0.0001

Data Index: 1354924 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.3956. Min Act: -0.0000

Data Index: 199879 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4298. Min Act: -0.0001

Data Index: 907496 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4620. Min Act: -0.0000

Data Index: 395173 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4410. Min Act: -0.0001

Data Index: 348284 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.8363. Min Range: -0.8363

Max Act: 0.4568. Min Act: -0.0000

Data Index: 855602 (C4 (Web Text))

Max Activating Token Index: 610