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

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

Neuron 4670 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1165000 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0567. Min Act: -0.0002

Data Index: 190548 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1107619 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0558. Min Act: -0.0002

Data Index: 586139 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1171298 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0544. Min Act: -0.0002

Data Index: 797677 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0543. Min Act: -0.0002

Data Index: 515942 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0539. Min Act: -0.0002

Data Index: 367789 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0512. Min Act: -0.0002

Data Index: 255416 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1261942 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0523. Min Act: -0.0002

Data Index: 414022 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0508. Min Act: -0.0002

Data Index: 922049 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0507. Min Act: -0.0002

Data Index: 404449 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1198375 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0503. Min Act: -0.0002

Data Index: 554569 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0498. Min Act: -0.0002

Data Index: 28101 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0487. Min Act: -0.0002

Data Index: 253869 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1309085 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1187400 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0504. Min Act: -0.0002

Data Index: 890331 (C4 (Web Text))

Max Activating Token Index: 154