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

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

Neuron 3299 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: 1.5417. Min Range: -1.5417

Max Act: 1.5417. Min Act: -0.0000

Data Index: 1594316 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.3369. Min Act: -0.0000

Data Index: 1364909 (Python Code)

Max Activating Token Index: 244

Text #2

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1500. Min Act: -0.0000

Data Index: 1496367 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1335. Min Act: -0.0000

Data Index: 1552428 (Python Code)

Max Activating Token Index: 14

Text #4

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1404027 (Python Code)

Max Activating Token Index: 167

Text #5

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1555599 (Python Code)

Max Activating Token Index: 26

Text #6

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1439795 (Python Code)

Max Activating Token Index: 538

Text #7

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1108. Min Act: -0.0001

Data Index: 1551461 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1447470 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.9676. Min Act: -0.0000

Data Index: 1451992 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1601712 (Python Code)

Max Activating Token Index: 12

Text #11

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.9442. Min Act: -0.0000

Data Index: 1445628 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1466475 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1412222 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1642021 (Python Code)

Max Activating Token Index: 533

Text #15

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1488543 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.8821. Min Act: -0.0001

Data Index: 1631063 (Python Code)

Max Activating Token Index: 179

Text #17

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1481136 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1581575 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1461525 (Python Code)

Max Activating Token Index: 191