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

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

Neuron 5703 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0696. Min Act: -0.0000

Data Index: 187371 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.2340. Min Act: -0.0000

Data Index: 133000 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0870. Min Act: -0.0000

Data Index: 671184 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0620. Min Act: -0.0000

Data Index: 1243339 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0424. Min Act: -0.0000

Data Index: 1187749 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.1043. Min Act: -0.0000

Data Index: 558486 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 2.2340. Min Range: -2.2340

Max Act: 1.9940. Min Act: -0.0000

Data Index: 1011933 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0830. Min Act: -0.0000

Data Index: 82684 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.1482. Min Act: -0.0000

Data Index: 739626 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0432. Min Act: -0.0000

Data Index: 1348447 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 2.2340. Min Range: -2.2340

Max Act: 1.9298. Min Act: -0.0000

Data Index: 530667 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.1192. Min Act: -0.0000

Data Index: 566289 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.1394. Min Act: -0.0000

Data Index: 212286 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0223. Min Act: -0.0000

Data Index: 1132178 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0074. Min Act: -0.0000

Data Index: 179113 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 2.2340. Min Range: -2.2340

Max Act: 1.8172. Min Act: -0.0000

Data Index: 244541 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0049. Min Act: -0.0000

Data Index: 290199 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 2.2340. Min Range: -2.2340

Max Act: 2.0111. Min Act: -0.0000

Data Index: 1181445 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 2.2340. Min Range: -2.2340

Max Act: 1.9852. Min Act: -0.0000

Data Index: 1157191 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 2.2340. Min Range: -2.2340

Max Act: 1.9002. Min Act: -0.0000

Data Index: 359734 (C4 (Web Text))

Max Activating Token Index: 315