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

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

Neuron 3096 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.1725. Min Act: -0.0000

Data Index: 319842 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1283524 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9312. Min Act: -0.0001

Data Index: 938225 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9063. Min Act: -0.0000

Data Index: 74467 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8726. Min Act: -0.0000

Data Index: 235165 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9474. Min Act: -0.0000

Data Index: 503718 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8791. Min Act: -0.0001

Data Index: 515577 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1215811 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9973. Min Act: -0.0001

Data Index: 96834 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8517. Min Act: -0.0000

Data Index: 382789 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9306. Min Act: -0.0000

Data Index: 793699 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1265085 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8639. Min Act: -0.0000

Data Index: 310269 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7937. Min Act: -0.0001

Data Index: 16318 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8082. Min Act: -0.0000

Data Index: 767380 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1078169 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9195. Min Act: -0.0000

Data Index: 557447 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7552. Min Act: -0.0001

Data Index: 584643 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7902. Min Act: -0.0000

Data Index: 686220 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7275. Min Act: -0.0001

Data Index: 538497 (C4 (Web Text))

Max Activating Token Index: 737