Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0003

Data Index: 837652 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1037425 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1349754 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0634. Min Act: -0.0003

Data Index: 669889 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0613. Min Act: -0.0002

Data Index: 924441 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0596. Min Act: -0.0003

Data Index: 75722 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0557. Min Act: -0.0003

Data Index: 769871 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0603. Min Act: -0.0003

Data Index: 477255 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0550. Min Act: -0.0003

Data Index: 320410 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0596. Min Act: -0.0003

Data Index: 296080 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0500. Min Act: -0.0003

Data Index: 959544 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0548. Min Act: -0.0003

Data Index: 13023 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0570. Min Act: -0.0003

Data Index: 81884 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0559. Min Act: -0.0003

Data Index: 378827 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0528. Min Act: -0.0003

Data Index: 133582 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0570. Min Act: -0.0003

Data Index: 810380 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0550. Min Act: -0.0003

Data Index: 481203 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0535. Min Act: -0.0003

Data Index: 907244 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0545. Min Act: -0.0003

Data Index: 793067 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0580. Min Act: -0.0003

Data Index: 805166 (C4 (Web Text))

Max Activating Token Index: 497