Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 673 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.4873. Min Act: -0.0000

Data Index: 963945 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.2673. Min Act: -0.0000

Data Index: 253875 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.2281. Min Act: -0.0000

Data Index: 654615 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.2949. Min Act: -0.0000

Data Index: 672289 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.1569. Min Act: -0.0000

Data Index: 516811 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.1580. Min Act: -0.0000

Data Index: 808941 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.2593. Min Act: -0.0000

Data Index: 626701 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.9529. Min Act: -0.0000

Data Index: 842124 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.0473. Min Act: -0.0000

Data Index: 884743 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.0339. Min Act: -0.0000

Data Index: 460704 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.9256. Min Act: -0.0000

Data Index: 1028661 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.9427. Min Act: -0.0000

Data Index: 1331988 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.0947. Min Act: -0.0000

Data Index: 1096038 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.1037. Min Act: -0.0000

Data Index: 762067 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.8786. Min Act: -0.0000

Data Index: 952527 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.9181. Min Act: -0.0000

Data Index: 922280 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.9189. Min Act: -0.0000

Data Index: 847809 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.8947. Min Act: -0.0000

Data Index: 482562 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 2.4873. Min Range: -2.4873

Max Act: 1.8729. Min Act: -0.0000

Data Index: 100165 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 2.4873. Min Range: -2.4873

Max Act: 2.0811. Min Act: -0.0000

Data Index: 272421 (C4 (Web Text))

Max Activating Token Index: 730