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

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

Neuron 3341 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0034. Min Range: -1.0034

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1626471 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.9326. Min Act: -0.0000

Data Index: 610318 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.8823. Min Act: -0.0000

Data Index: 491082 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.8219. Min Act: -0.0000

Data Index: 121156 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.8039. Min Act: -0.0000

Data Index: 188312 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.7978. Min Act: -0.0000

Data Index: 227512 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.7855. Min Act: -0.0000

Data Index: 264363 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1254226 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1048629 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6793. Min Act: -0.0000

Data Index: 503023 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.7007. Min Act: -0.0000

Data Index: 147262 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6531. Min Act: -0.0000

Data Index: 479113 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6918. Min Act: -0.0000

Data Index: 802048 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1265646 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6593. Min Act: -0.0000

Data Index: 726689 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1113153 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1563650 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6519. Min Act: -0.0000

Data Index: 367101 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6307. Min Act: -0.0000

Data Index: 422874 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.0034. Min Range: -1.0034

Max Act: 0.6381. Min Act: -0.0000

Data Index: 596125 (C4 (Web Text))

Max Activating Token Index: 879