Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 93 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 1.0112. Min Range: -1.0112

Max Act: 1.0112. Min Act: -0.0005

Data Index: 346806 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.9321. Min Act: -0.0005

Data Index: 857909 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7471. Min Act: -0.0005

Data Index: 445797 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.8314. Min Act: -0.0005

Data Index: 567315 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.8201. Min Act: -0.0005

Data Index: 206902 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7374. Min Act: -0.0005

Data Index: 20286 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7123. Min Act: -0.0005

Data Index: 1234633 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7140. Min Act: -0.0005

Data Index: 1320954 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7300. Min Act: -0.0005

Data Index: 595364 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6853. Min Act: -0.0005

Data Index: 1336079 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7007. Min Act: -0.0005

Data Index: 311868 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7183. Min Act: -0.0005

Data Index: 476649 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6778. Min Act: -0.0005

Data Index: 1296843 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7374. Min Act: -0.0005

Data Index: 367037 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6853. Min Act: -0.0005

Data Index: 417122 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6795. Min Act: -0.0005

Data Index: 348507 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.7058. Min Act: -0.0005

Data Index: 1105864 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6248. Min Act: -0.0005

Data Index: 529969 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6249. Min Act: -0.0005

Data Index: 245757 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.0112. Min Range: -1.0112

Max Act: 0.6675. Min Act: -0.0005

Data Index: 736989 (C4 (Web Text))

Max Activating Token Index: 39