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

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

Neuron 507 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7839. Min Act: -0.0000

Data Index: 1580338 (Python Code)

Max Activating Token Index: 499

Text #1

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.8484. Min Act: -0.0000

Data Index: 1596167 (Python Code)

Max Activating Token Index: 898

Text #2

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6167. Min Act: -0.0000

Data Index: 1460918 (Python Code)

Max Activating Token Index: 270

Text #3

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.3883. Min Act: -0.0000

Data Index: 1603618 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.6807. Min Act: -0.0000

Data Index: 1503274 (Python Code)

Max Activating Token Index: 436

Text #5

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.7225. Min Act: -0.0000

Data Index: 1409838 (Python Code)

Max Activating Token Index: 301

Text #6

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.4501. Min Act: -0.0000

Data Index: 1368350 (Python Code)

Max Activating Token Index: 896

Text #7

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.0781. Min Act: -0.0000

Data Index: 1599507 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.2098. Min Act: -0.0000

Data Index: 1564094 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.0353. Min Act: -0.0000

Data Index: 1557919 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.0550. Min Act: -0.0000

Data Index: 1401157 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.0170. Min Act: -0.0000

Data Index: 1494341 (Python Code)

Max Activating Token Index: 236

Text #12

Max Range: 3.8484. Min Range: -3.8484

Max Act: 2.7593. Min Act: -0.0000

Data Index: 1551131 (Python Code)

Max Activating Token Index: 173

Text #13

Max Range: 3.8484. Min Range: -3.8484

Max Act: 3.0177. Min Act: -0.0000

Data Index: 1478549 (Python Code)

Max Activating Token Index: 689

Text #14

Max Range: 3.8484. Min Range: -3.8484

Max Act: 2.7398. Min Act: -0.0000

Data Index: 1417083 (Python Code)

Max Activating Token Index: 68

Text #15

Max Range: 3.8484. Min Range: -3.8484

Max Act: 2.6584. Min Act: -0.0000

Data Index: 1533306 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 3.8484. Min Range: -3.8484

Max Act: 2.7817. Min Act: -0.0000

Data Index: 1577149 (Python Code)

Max Activating Token Index: 933

Text #17

Max Range: 3.8484. Min Range: -3.8484

Max Act: 2.8947. Min Act: -0.0000

Data Index: 1531386 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 3.8484. Min Range: -3.8484

Max Act: 2.6326. Min Act: -0.0000

Data Index: 1503866 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 3.8484. Min Range: -3.8484

Max Act: 2.6085. Min Act: -0.0000

Data Index: 1569380 (Python Code)

Max Activating Token Index: 743