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

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

Neuron 1290 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: 1.7935. Min Range: -1.7935

Max Act: 1.7935. Min Act: -0.0000

Data Index: 1465848 (Python Code)

Max Activating Token Index: 814

Text #1

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6876. Min Act: -0.0000

Data Index: 1625276 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.7158. Min Act: -0.0000

Data Index: 1596179 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6777. Min Act: -0.0000

Data Index: 1625514 (Python Code)

Max Activating Token Index: 320

Text #4

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5634. Min Act: -0.0000

Data Index: 1553537 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5883. Min Act: -0.0000

Data Index: 1485094 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6267. Min Act: -0.0000

Data Index: 1596029 (Python Code)

Max Activating Token Index: 829

Text #7

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5659. Min Act: -0.0000

Data Index: 1483510 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5226. Min Act: -0.0000

Data Index: 1446774 (Python Code)

Max Activating Token Index: 785

Text #9

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1477278 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1491759 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.4202. Min Act: -0.0000

Data Index: 1593786 (Python Code)

Max Activating Token Index: 237

Text #12

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.6486. Min Act: -0.0000

Data Index: 1418737 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5022. Min Act: -0.0000

Data Index: 1573917 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5412. Min Act: -0.0000

Data Index: 1637302 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1585033 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.4777. Min Act: -0.0000

Data Index: 1411153 (Python Code)

Max Activating Token Index: 588

Text #17

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1524787 (Python Code)

Max Activating Token Index: 183

Text #18

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5540. Min Act: -0.0000

Data Index: 1644538 (Python Code)

Max Activating Token Index: 918

Text #19

Max Range: 1.7935. Min Range: -1.7935

Max Act: 1.5000. Min Act: -0.0000

Data Index: 1403507 (Python Code)

Max Activating Token Index: 577