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

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

Neuron 5151 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1363. Min Range: -1.1363

Max Act: 1.1363. Min Act: -0.0000

Data Index: 322843 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 1.1363. Min Range: -1.1363

Max Act: 1.0168. Min Act: -0.0000

Data Index: 390169 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.1363. Min Range: -1.1363

Max Act: 1.0317. Min Act: -0.0000

Data Index: 560511 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.9884. Min Act: -0.0000

Data Index: 922638 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.9169. Min Act: -0.0000

Data Index: 494221 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.9728. Min Act: -0.0000

Data Index: 379160 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8992. Min Act: -0.0000

Data Index: 289794 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1388913 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1377602 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8693. Min Act: -0.0000

Data Index: 134859 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.9289. Min Act: -0.0000

Data Index: 199242 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1514725 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8976. Min Act: -0.0000

Data Index: 615737 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.9698. Min Act: -0.0000

Data Index: 669268 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1568019 (Python Code)

Max Activating Token Index: 115

Text #15

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1526626 (Python Code)

Max Activating Token Index: 69

Text #16

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8419. Min Act: -0.0000

Data Index: 920055 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1517991 (Python Code)

Max Activating Token Index: 86

Text #18

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1421855 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 1.1363. Min Range: -1.1363

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1457008 (Python Code)

Max Activating Token Index: 97