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

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

Neuron 516 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: 0.6650. Min Range: -0.6650

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1433043 (Python Code)

Max Activating Token Index: 541

Text #1

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1594126 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1651486 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1442926 (Python Code)

Max Activating Token Index: 272

Text #4

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1446427 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1533502 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1542705 (Python Code)

Max Activating Token Index: 385

Text #7

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1633545 (Python Code)

Max Activating Token Index: 804

Text #8

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1372909 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1569507 (Python Code)

Max Activating Token Index: 419

Text #10

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1629037 (Python Code)

Max Activating Token Index: 551

Text #11

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1423206 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1597285 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1628157 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1403623 (Python Code)

Max Activating Token Index: 295

Text #15

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1490499 (Python Code)

Max Activating Token Index: 358

Text #16

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1625757 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1381106 (Python Code)

Max Activating Token Index: 446

Text #18

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1464283 (Python Code)

Max Activating Token Index: 504

Text #19

Max Range: 0.6650. Min Range: -0.6650

Max Act: 0.3920. Min Act: -0.0000

Data Index: 1580100 (Python Code)

Max Activating Token Index: 912