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

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

Neuron 2610 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.9254. Min Act: -0.0001

Data Index: 815669 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.9377. Min Act: -0.0001

Data Index: 176249 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 1.0085. Min Range: -1.0085

Max Act: 1.0085. Min Act: -0.0001

Data Index: 158055 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8348. Min Act: -0.0001

Data Index: 86518 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8062. Min Act: -0.0001

Data Index: 1300222 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8141. Min Act: -0.0001

Data Index: 694777 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8498. Min Act: -0.0001

Data Index: 1224432 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8230. Min Act: -0.0001

Data Index: 412692 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.7621. Min Act: -0.0001

Data Index: 1132621 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8038. Min Act: -0.0001

Data Index: 1191872 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8069. Min Act: -0.0001

Data Index: 656377 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8042. Min Act: -0.0001

Data Index: 1158765 (C4 (Web Text))

Max Activating Token Index: 300

Text #12

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8038. Min Act: -0.0001

Data Index: 775712 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.7759. Min Act: -0.0001

Data Index: 806032 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.7956. Min Act: -0.0001

Data Index: 1076189 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.7957. Min Act: -0.0001

Data Index: 477388 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8115. Min Act: -0.0001

Data Index: 545724 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.7901. Min Act: -0.0001

Data Index: 1080488 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.7867. Min Act: -0.0001

Data Index: 73737 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.0085. Min Range: -1.0085

Max Act: 0.8080. Min Act: -0.0001

Data Index: 1069441 (C4 (Web Text))

Max Activating Token Index: 419