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

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

Neuron 1733 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1114. Min Act: -0.0001

Data Index: 931799 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.4576. Min Act: -0.0001

Data Index: 1014312 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.4768. Min Act: -0.0001

Data Index: 128677 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.3578. Min Act: -0.0001

Data Index: 847931 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2229. Min Act: -0.0001

Data Index: 431912 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2038. Min Act: -0.0001

Data Index: 1132359 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.0260. Min Act: -0.0001

Data Index: 360844 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 1.4768. Min Range: -1.4768

Max Act: 0.9129. Min Act: -0.0001

Data Index: 127250 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.2088. Min Act: -0.0001

Data Index: 816908 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.4768. Min Range: -1.4768

Max Act: 0.9752. Min Act: -0.0001

Data Index: 1261778 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1450. Min Act: -0.0001

Data Index: 1300541 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.0486. Min Act: -0.0001

Data Index: 63050 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1053. Min Act: -0.0001

Data Index: 1422510 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1153. Min Act: -0.0001

Data Index: 1196488 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1580. Min Act: -0.0001

Data Index: 825963 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.0456. Min Act: -0.0001

Data Index: 861171 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.0232. Min Act: -0.0001

Data Index: 1216275 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.0593. Min Act: -0.0001

Data Index: 1513857 (Python Code)

Max Activating Token Index: 417

Text #18

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.0024. Min Act: -0.0001

Data Index: 1085787 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 1.4768. Min Range: -1.4768

Max Act: 1.1738. Min Act: -0.0001

Data Index: 474250 (C4 (Web Text))

Max Activating Token Index: 818