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

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

Neuron 5434 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.3945. Min Act: -0.0002

Data Index: 1070982 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2462. Min Act: -0.0002

Data Index: 147480 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2114. Min Act: -0.0002

Data Index: 1064614 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1541. Min Act: -0.0002

Data Index: 72359 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1322. Min Act: -0.0002

Data Index: 951035 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1038. Min Act: -0.0002

Data Index: 792488 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1034. Min Act: -0.0002

Data Index: 1261434 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0938. Min Act: -0.0003

Data Index: 1335241 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1064. Min Act: -0.0002

Data Index: 398595 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0877. Min Act: -0.0002

Data Index: 1332956 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0863. Min Act: -0.0002

Data Index: 1098794 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0788. Min Act: -0.0002

Data Index: 1279212 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0916. Min Act: -0.0002

Data Index: 467245 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0922. Min Act: -0.0003

Data Index: 1066302 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0652. Min Act: -0.0002

Data Index: 573344 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0524. Min Act: -0.0002

Data Index: 447674 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0773. Min Act: -0.0002

Data Index: 47360 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0600. Min Act: -0.0002

Data Index: 48984 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0608. Min Act: -0.0002

Data Index: 915636 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0609. Min Act: -0.0002

Data Index: 1147500 (C4 (Web Text))

Max Activating Token Index: 289