Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 891 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0004

Data Index: 280048 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0199. Min Act: -0.0004

Data Index: 1129344 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0212. Min Act: -0.0004

Data Index: 773735 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0206. Min Act: -0.0004

Data Index: 1378507 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0202. Min Act: -0.0004

Data Index: 278688 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0202. Min Act: -0.0004

Data Index: 960230 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0199. Min Act: -0.0004

Data Index: 485235 (C4 (Web Text))

Max Activating Token Index: 12

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0198. Min Act: -0.0004

Data Index: 170078 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0202. Min Act: -0.0004

Data Index: 308525 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0200. Min Act: -0.0004

Data Index: 1397715 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0193. Min Act: -0.0004

Data Index: 578699 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0194. Min Act: -0.0004

Data Index: 1096180 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1087807 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0183. Min Act: -0.0004

Data Index: 1487986 (Python Code)

Max Activating Token Index: 110

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0189. Min Act: -0.0004

Data Index: 1576651 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0186. Min Act: -0.0004

Data Index: 1438572 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0183. Min Act: -0.0004

Data Index: 1109191 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0184. Min Act: -0.0004

Data Index: 215518 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0191. Min Act: -0.0004

Data Index: 947501 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0181. Min Act: -0.0004

Data Index: 950764 (C4 (Web Text))

Max Activating Token Index: 8