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

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

Neuron 1268 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0646. Min Act: -0.0002

Data Index: 88183 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1002540 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0582. Min Act: -0.0001

Data Index: 835777 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0569. Min Act: -0.0000

Data Index: 345378 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0581. Min Act: 0.0000

Data Index: 1217235 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0576. Min Act: -0.0002

Data Index: 881874 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0554. Min Act: -0.0002

Data Index: 402235 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0565. Min Act: -0.0002

Data Index: 875206 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0533. Min Act: -0.0001

Data Index: 731886 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0549. Min Act: -0.0001

Data Index: 779830 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0555. Min Act: -0.0002

Data Index: 837089 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0548. Min Act: 0.0002

Data Index: 230178 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0546. Min Act: -0.0002

Data Index: 800092 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0533. Min Act: 0.0001

Data Index: 1251451 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0537. Min Act: -0.0002

Data Index: 696735 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0539. Min Act: 0.0001

Data Index: 529356 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0555. Min Act: 0.0001

Data Index: 1250442 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0532. Min Act: -0.0000

Data Index: 612462 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0516. Min Act: 0.0001

Data Index: 775386 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0646. Min Range: -0.0646

Max Act: 0.0520. Min Act: 0.0002

Data Index: 792845 (C4 (Web Text))

Max Activating Token Index: 1017