Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1570 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6974. Min Act: -0.0002

Data Index: 616003 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6382. Min Act: -0.0002

Data Index: 753411 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5564. Min Act: -0.0001

Data Index: 546370 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5824. Min Act: -0.0001

Data Index: 1093850 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5502. Min Act: -0.0002

Data Index: 469466 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5487. Min Act: -0.0002

Data Index: 620962 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5421. Min Act: -0.0002

Data Index: 206480 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5127. Min Act: -0.0001

Data Index: 1206976 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4905. Min Act: -0.0002

Data Index: 567862 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5138. Min Act: -0.0001

Data Index: 992653 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4817. Min Act: -0.0002

Data Index: 1296605 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5020. Min Act: -0.0002

Data Index: 275552 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5271. Min Act: -0.0001

Data Index: 278241 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5545. Min Act: -0.0001

Data Index: 1163410 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5107. Min Act: -0.0002

Data Index: 1198559 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4905. Min Act: -0.0002

Data Index: 1010424 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5427. Min Act: -0.0002

Data Index: 1263505 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4868. Min Act: -0.0002

Data Index: 1068204 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.4728. Min Act: -0.0001

Data Index: 53628 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5156. Min Act: -0.0002

Data Index: 695243 (C4 (Web Text))

Max Activating Token Index: 873