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

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

Neuron 480 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: 1.8462. Min Range: -1.8462

Max Act: 1.8462. Min Act: -0.0000

Data Index: 1206147 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.6434. Min Act: -0.0000

Data Index: 1244301 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.5991. Min Act: -0.0000

Data Index: 1254647 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.4340. Min Act: -0.0000

Data Index: 1211024 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.4942. Min Act: -0.0000

Data Index: 1262960 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.3868. Min Act: -0.0000

Data Index: 488393 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.4146. Min Act: -0.0000

Data Index: 1036508 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1066798 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2689. Min Act: -0.0000

Data Index: 404255 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2028. Min Act: -0.0000

Data Index: 505869 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2243. Min Act: -0.0000

Data Index: 282304 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.3245. Min Act: -0.0000

Data Index: 980237 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.3071. Min Act: -0.0000

Data Index: 563950 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2337. Min Act: -0.0000

Data Index: 916946 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.1788. Min Act: -0.0000

Data Index: 211683 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.1234. Min Act: -0.0000

Data Index: 153992 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2017. Min Act: -0.0000

Data Index: 732541 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.1241. Min Act: -0.0000

Data Index: 706523 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2257. Min Act: -0.0000

Data Index: 893965 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 1.8462. Min Range: -1.8462

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1225668 (C4 (Web Text))

Max Activating Token Index: 794