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

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

Neuron 4572 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.6086. Min Act: -0.0000

Data Index: 313578 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.5062. Min Act: -0.0000

Data Index: 905232 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.5018. Min Act: -0.0000

Data Index: 76628 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1089255 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1128421 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3393. Min Act: -0.0000

Data Index: 1229128 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3557. Min Act: -0.0000

Data Index: 115487 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3404. Min Act: -0.0000

Data Index: 818317 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3403. Min Act: -0.0000

Data Index: 30232 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2887. Min Act: -0.0000

Data Index: 255853 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1414243 (Python Code)

Max Activating Token Index: 220

Text #11

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.3047. Min Act: -0.0000

Data Index: 684526 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1573507 (Python Code)

Max Activating Token Index: 720

Text #13

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1489336 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1637762 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1373343 (Python Code)

Max Activating Token Index: 922

Text #16

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1233653 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1586737 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1648294 (Python Code)

Max Activating Token Index: 315

Text #19

Max Range: 0.6086. Min Range: -0.6086

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1444002 (Python Code)

Max Activating Token Index: 691