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

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

Neuron 4338 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1512484 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.3029. Min Act: -0.0000

Data Index: 1544692 (Python Code)

Max Activating Token Index: 566

Text #2

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1530608 (Python Code)

Max Activating Token Index: 680

Text #3

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1468968 (Python Code)

Max Activating Token Index: 832

Text #4

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2844. Min Act: -0.0000

Data Index: 1641137 (Python Code)

Max Activating Token Index: 253

Text #5

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1585218 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1581405 (Python Code)

Max Activating Token Index: 171

Text #7

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2586. Min Act: -0.0001

Data Index: 1361744 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2471. Min Act: -0.0001

Data Index: 1596950 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2614. Min Act: -0.0000

Data Index: 212476 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1377827 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1389658 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1517617 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1648955 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1599105 (Python Code)

Max Activating Token Index: 952

Text #15

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1593729 (Python Code)

Max Activating Token Index: 574

Text #16

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1568403 (Python Code)

Max Activating Token Index: 833

Text #17

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1582188 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1596330 (Python Code)

Max Activating Token Index: 221

Text #19

Max Range: 0.3301. Min Range: -0.3301

Max Act: 0.2404. Min Act: -0.0000

Data Index: 1367246 (Python Code)

Max Activating Token Index: 657