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

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

Neuron 2963 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0328. Min Range: -1.0328

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1520290 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1510067 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1446356 (Python Code)

Max Activating Token Index: 427

Text #3

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1622917 (Python Code)

Max Activating Token Index: 159

Text #4

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1606269 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1282861 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1590216 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1612771 (Python Code)

Max Activating Token Index: 526

Text #8

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7994. Min Act: -0.0000

Data Index: 1474829 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1417613 (Python Code)

Max Activating Token Index: 865

Text #10

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1402563 (Python Code)

Max Activating Token Index: 152

Text #11

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1430899 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7274. Min Act: -0.0000

Data Index: 1437842 (Python Code)

Max Activating Token Index: 537

Text #13

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1428021 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1489064 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1602982 (Python Code)

Max Activating Token Index: 829

Text #16

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1405356 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1480324 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.6658. Min Act: -0.0000

Data Index: 526914 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 1.0328. Min Range: -1.0328

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1625056 (Python Code)

Max Activating Token Index: 116