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

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

Neuron 3592 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2736. Min Act: -0.0000

Data Index: 110291 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2850. Min Act: -0.0000

Data Index: 889986 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1330340 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2692. Min Act: -0.0000

Data Index: 465417 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2572. Min Act: -0.0000

Data Index: 718345 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1329353 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1090355 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2269. Min Act: -0.0000

Data Index: 178453 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2289. Min Act: -0.0000

Data Index: 317891 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2565. Min Act: -0.0000

Data Index: 518156 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2174. Min Act: -0.0000

Data Index: 1220493 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2352. Min Act: -0.0000

Data Index: 454905 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2204. Min Act: -0.0000

Data Index: 391832 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2161. Min Act: -0.0000

Data Index: 589490 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1220154 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1743. Min Act: -0.0000

Data Index: 50567 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1176606 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1950. Min Act: -0.0000

Data Index: 19264 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1642. Min Act: -0.0000

Data Index: 180932 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1009651 (C4 (Web Text))

Max Activating Token Index: 974