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

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

Neuron 4633 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: 3.8546. Min Range: -3.8546

Max Act: 3.8546. Min Act: -0.0000

Data Index: 1289408 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.7909. Min Act: -0.0000

Data Index: 697006 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.3619. Min Act: -0.0000

Data Index: 1296507 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.4300. Min Act: -0.0000

Data Index: 700898 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.4858. Min Act: -0.0000

Data Index: 2732 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.2649. Min Act: -0.0000

Data Index: 1054068 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.8427. Min Act: -0.0000

Data Index: 838518 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.7585. Min Act: -0.0000

Data Index: 1180734 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.7461. Min Act: -0.0000

Data Index: 1283667 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.8461. Min Act: -0.0000

Data Index: 1279715 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.9444. Min Act: -0.0000

Data Index: 840925 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.9363. Min Act: -0.0000

Data Index: 1241974 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.8973. Min Act: -0.0000

Data Index: 723756 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.9003. Min Act: -0.0000

Data Index: 404740 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.6016. Min Act: -0.0000

Data Index: 137013 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.5924. Min Act: -0.0000

Data Index: 769444 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.7202. Min Act: -0.0000

Data Index: 195895 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.5835. Min Act: -0.0000

Data Index: 911553 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.8491. Min Act: -0.0000

Data Index: 172430 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.3289. Min Act: -0.0000

Data Index: 589111 (C4 (Web Text))

Max Activating Token Index: 251