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

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

Neuron 1734 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1364534 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4800. Min Act: -0.0000

Data Index: 660257 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4974. Min Act: -0.0000

Data Index: 1479455 (Python Code)

Max Activating Token Index: 760

Text #3

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3755. Min Act: -0.0000

Data Index: 855302 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3694. Min Act: -0.0000

Data Index: 1380314 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1511504 (Python Code)

Max Activating Token Index: 413

Text #6

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1356122 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4328. Min Act: -0.0000

Data Index: 297250 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4079. Min Act: -0.0000

Data Index: 231327 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1623399 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1601786 (Python Code)

Max Activating Token Index: 573

Text #11

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1508519 (Python Code)

Max Activating Token Index: 772

Text #12

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3768. Min Act: -0.0000

Data Index: 787720 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4124. Min Act: -0.0000

Data Index: 317294 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1398314 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3656. Min Act: -0.0000

Data Index: 253304 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3789. Min Act: -0.0000

Data Index: 478518 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3454. Min Act: -0.0000

Data Index: 746182 (C4 (Web Text))

Max Activating Token Index: 427

Text #18

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3218. Min Act: -0.0000

Data Index: 720496 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1022466 (C4 (Web Text))

Max Activating Token Index: 562