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

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

Neuron 4399 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2036. Min Range: -4.2036

Max Act: 4.2036. Min Act: -0.0000

Data Index: 1160780 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.8634. Min Act: -0.0000

Data Index: 64181 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.6924. Min Act: -0.0000

Data Index: 156633 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.2960. Min Act: -0.0000

Data Index: 220302 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.6252. Min Act: -0.0000

Data Index: 67727 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.4304. Min Act: -0.0000

Data Index: 875238 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.2344. Min Act: -0.0000

Data Index: 139992 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.1617. Min Act: -0.0000

Data Index: 1227666 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.0169. Min Act: -0.0000

Data Index: 332863 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 4.2036. Min Range: -4.2036

Max Act: 2.9772. Min Act: -0.0000

Data Index: 1183378 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.0610. Min Act: -0.0000

Data Index: 697998 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 4.2036. Min Range: -4.2036

Max Act: 2.6742. Min Act: -0.0000

Data Index: 923467 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.0926. Min Act: -0.0000

Data Index: 535101 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.0537. Min Act: -0.0000

Data Index: 289527 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 4.2036. Min Range: -4.2036

Max Act: 3.0407. Min Act: -0.0000

Data Index: 1034023 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 4.2036. Min Range: -4.2036

Max Act: 2.8450. Min Act: -0.0000

Data Index: 168967 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 4.2036. Min Range: -4.2036

Max Act: 2.6793. Min Act: -0.0000

Data Index: 501464 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 4.2036. Min Range: -4.2036

Max Act: 2.3935. Min Act: -0.0000

Data Index: 1237694 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 4.2036. Min Range: -4.2036

Max Act: 2.6426. Min Act: -0.0000

Data Index: 357040 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 4.2036. Min Range: -4.2036

Max Act: 2.6461. Min Act: -0.0000

Data Index: 230736 (C4 (Web Text))

Max Activating Token Index: 563