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

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

Neuron 4732 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: 0.9673. Min Range: -0.9673

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1587360 (Python Code)

Max Activating Token Index: 259

Text #1

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1572370 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.9496. Min Act: -0.0000

Data Index: 1578839 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1562176 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1434076 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1495918 (Python Code)

Max Activating Token Index: 410

Text #6

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1530928 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1474765 (Python Code)

Max Activating Token Index: 566

Text #8

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1574903 (Python Code)

Max Activating Token Index: 653

Text #9

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1483594 (Python Code)

Max Activating Token Index: 398

Text #10

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8768. Min Act: -0.0000

Data Index: 1586733 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1493857 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1510363 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1512912 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1520831 (Python Code)

Max Activating Token Index: 484

Text #15

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1519560 (Python Code)

Max Activating Token Index: 696

Text #16

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1498139 (Python Code)

Max Activating Token Index: 713

Text #17

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1497080 (Python Code)

Max Activating Token Index: 399

Text #18

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1500940 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 0.9673. Min Range: -0.9673

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1590317 (Python Code)

Max Activating Token Index: 201