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

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

Neuron 4601 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: 1.6409. Min Range: -1.6409

Max Act: 1.6409. Min Act: -0.0001

Data Index: 1074249 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.4985. Min Act: -0.0001

Data Index: 645668 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.4668. Min Act: -0.0001

Data Index: 5514 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.1338. Min Act: -0.0000

Data Index: 712821 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.3194. Min Act: -0.0000

Data Index: 387629 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2112. Min Act: -0.0001

Data Index: 1335172 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.3182. Min Act: -0.0000

Data Index: 906182 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2791. Min Act: -0.0001

Data Index: 754902 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2000. Min Act: -0.0001

Data Index: 653860 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.4210. Min Act: -0.0000

Data Index: 88862 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2037. Min Act: -0.0000

Data Index: 439126 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2844. Min Act: -0.0000

Data Index: 782233 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2472. Min Act: -0.0001

Data Index: 808214 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.1864. Min Act: -0.0000

Data Index: 162545 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2100. Min Act: -0.0000

Data Index: 8286 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2408. Min Act: -0.0000

Data Index: 175099 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.1245. Min Act: -0.0000

Data Index: 1092736 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2302. Min Act: -0.0001

Data Index: 680169 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.2146. Min Act: -0.0000

Data Index: 612137 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 1.6409. Min Range: -1.6409

Max Act: 1.1431. Min Act: -0.0001

Data Index: 635747 (C4 (Web Text))

Max Activating Token Index: 933