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

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

Neuron 3010 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2683. Min Act: -0.0000

Data Index: 92790 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2058. Min Act: -0.0000

Data Index: 123875 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2092. Min Act: -0.0000

Data Index: 1301377 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.2082. Min Act: 0.0000

Data Index: 405317 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1359492 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1789. Min Act: -0.0000

Data Index: 444666 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1760. Min Act: -0.0000

Data Index: 801619 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1792. Min Act: -0.0000

Data Index: 472977 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1729. Min Act: -0.0000

Data Index: 899873 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1684. Min Act: -0.0000

Data Index: 195410 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1314467 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1632. Min Act: -0.0000

Data Index: 181323 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1609. Min Act: -0.0000

Data Index: 562696 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1617. Min Act: -0.0000

Data Index: 428616 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1664. Min Act: 0.0000

Data Index: 164466 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1655. Min Act: -0.0000

Data Index: 231782 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1531. Min Act: -0.0000

Data Index: 24932 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1571. Min Act: -0.0000

Data Index: 1220168 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1506. Min Act: 0.0000

Data Index: 1221270 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.2683. Min Range: -0.2683

Max Act: 0.1490. Min Act: 0.0001

Data Index: 535289 (C4 (Web Text))

Max Activating Token Index: 63