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

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

Neuron 3131 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2618. Min Act: -0.0001

Data Index: 489956 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2346. Min Act: -0.0001

Data Index: 78527 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2200. Min Act: -0.0001

Data Index: 930133 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2196. Min Act: -0.0001

Data Index: 1185670 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2189. Min Act: -0.0001

Data Index: 459474 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2300. Min Act: -0.0001

Data Index: 783282 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2213. Min Act: -0.0001

Data Index: 824024 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1015443 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2141. Min Act: -0.0001

Data Index: 642472 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1976. Min Act: -0.0001

Data Index: 26379 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2078. Min Act: -0.0001

Data Index: 1027059 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2066. Min Act: -0.0001

Data Index: 303909 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2146. Min Act: -0.0001

Data Index: 1204444 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1892. Min Act: -0.0001

Data Index: 799326 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2021. Min Act: -0.0001

Data Index: 749531 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1802. Min Act: -0.0001

Data Index: 629818 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1908. Min Act: -0.0001

Data Index: 1257528 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1007976 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1877. Min Act: -0.0001

Data Index: 365875 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1903. Min Act: -0.0001

Data Index: 972523 (C4 (Web Text))

Max Activating Token Index: 613