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

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

Neuron 1598 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5793. Min Range: -2.5793

Max Act: 2.5793. Min Act: -0.0000

Data Index: 1390123 (Python Code)

Max Activating Token Index: 510

Text #1

Max Range: 2.5793. Min Range: -2.5793

Max Act: 1.8228. Min Act: -0.0000

Data Index: 1371196 (Python Code)

Max Activating Token Index: 282

Text #2

Max Range: 2.5793. Min Range: -2.5793

Max Act: 1.7090. Min Act: -0.0000

Data Index: 1496410 (Python Code)

Max Activating Token Index: 609

Text #3

Max Range: 2.5793. Min Range: -2.5793

Max Act: 1.2407. Min Act: -0.0000

Data Index: 1609682 (Python Code)

Max Activating Token Index: 567

Text #4

Max Range: 2.5793. Min Range: -2.5793

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1367309 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 2.5793. Min Range: -2.5793

Max Act: 1.0847. Min Act: -0.0000

Data Index: 1436217 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 2.5793. Min Range: -2.5793

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1479093 (Python Code)

Max Activating Token Index: 526

Text #7

Max Range: 2.5793. Min Range: -2.5793

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1447003 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 2.5793. Min Range: -2.5793

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1418584 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1402980 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.9538. Min Act: -0.0000

Data Index: 1365553 (Python Code)

Max Activating Token Index: 321

Text #11

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1608928 (Python Code)

Max Activating Token Index: 953

Text #12

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1580656 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1557504 (Python Code)

Max Activating Token Index: 355

Text #14

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.9399. Min Act: -0.0000

Data Index: 1564467 (Python Code)

Max Activating Token Index: 679

Text #15

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1440644 (Python Code)

Max Activating Token Index: 396

Text #16

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1504507 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1366332 (Python Code)

Max Activating Token Index: 386

Text #18

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1632928 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 2.5793. Min Range: -2.5793

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1655145 (Python Code)

Max Activating Token Index: 758