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

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

Neuron 4076 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0791. Min Act: -0.0002

Data Index: 626758 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0541. Min Act: -0.0002

Data Index: 145164 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0529. Min Act: -0.0002

Data Index: 560096 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1065429 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0536. Min Act: -0.0002

Data Index: 179942 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0472. Min Act: -0.0002

Data Index: 62406 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0484. Min Act: -0.0002

Data Index: 838226 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0464. Min Act: -0.0002

Data Index: 252617 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1174123 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0457. Min Act: -0.0002

Data Index: 169193 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1057130 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0456. Min Act: -0.0002

Data Index: 180563 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0437. Min Act: -0.0002

Data Index: 23172 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0443. Min Act: -0.0002

Data Index: 94074 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1292560 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0442. Min Act: -0.0002

Data Index: 813993 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0417. Min Act: -0.0002

Data Index: 762022 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0430. Min Act: -0.0002

Data Index: 859105 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1262129 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0424. Min Act: -0.0002

Data Index: 496600 (C4 (Web Text))

Max Activating Token Index: 660