Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1366 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5265. Min Act: -0.0000

Data Index: 1649555 (Python Code)

Max Activating Token Index: 51

Text #1

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.5483. Min Act: -0.0000

Data Index: 1595248 (Python Code)

Max Activating Token Index: 156

Text #2

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.4976. Min Act: -0.0000

Data Index: 1568419 (Python Code)

Max Activating Token Index: 524

Text #3

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1498197 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.6560. Min Act: -0.0000

Data Index: 1505137 (Python Code)

Max Activating Token Index: 245

Text #5

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.3902. Min Act: -0.0000

Data Index: 1501414 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.3529. Min Act: -0.0000

Data Index: 1589513 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.3293. Min Act: -0.0000

Data Index: 1605934 (Python Code)

Max Activating Token Index: 310

Text #8

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.1965. Min Act: -0.0000

Data Index: 1617992 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.2069. Min Act: -0.0000

Data Index: 1493182 (Python Code)

Max Activating Token Index: 1008

Text #10

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.1751. Min Act: -0.0000

Data Index: 1398502 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.1671. Min Act: -0.0000

Data Index: 1564577 (Python Code)

Max Activating Token Index: 811

Text #12

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.2834. Min Act: -0.0000

Data Index: 1399835 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 2.6560. Min Range: -2.6560

Max Act: 1.9107. Min Act: -0.0000

Data Index: 1514709 (Python Code)

Max Activating Token Index: 341

Text #14

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.2253. Min Act: -0.0000

Data Index: 1488259 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.0517. Min Act: -0.0000

Data Index: 1567516 (Python Code)

Max Activating Token Index: 319

Text #16

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.3200. Min Act: -0.0000

Data Index: 1586943 (Python Code)

Max Activating Token Index: 334

Text #17

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.3149. Min Act: -0.0000

Data Index: 1628699 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.0422. Min Act: -0.0000

Data Index: 1452698 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 2.6560. Min Range: -2.6560

Max Act: 2.1526. Min Act: -0.0000

Data Index: 1374100 (Python Code)

Max Activating Token Index: 520