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

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

Neuron 3212 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.8515. Min Act: -0.0000

Data Index: 1496229 (Python Code)

Max Activating Token Index: 505

Text #1

Max Range: 5.0253. Min Range: -5.0253

Max Act: 5.0253. Min Act: -0.0000

Data Index: 1581314 (Python Code)

Max Activating Token Index: 866

Text #2

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.7983. Min Act: 0.0000

Data Index: 1635247 (Python Code)

Max Activating Token Index: 567

Text #3

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.5399. Min Act: -0.0000

Data Index: 1535013 (Python Code)

Max Activating Token Index: 845

Text #4

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.5463. Min Act: -0.0000

Data Index: 1508263 (Python Code)

Max Activating Token Index: 637

Text #5

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.5385. Min Act: -0.0000

Data Index: 1368863 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.5226. Min Act: -0.0000

Data Index: 1451569 (Python Code)

Max Activating Token Index: 1001

Text #7

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.4782. Min Act: -0.0000

Data Index: 1575957 (Python Code)

Max Activating Token Index: 527

Text #8

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.2769. Min Act: -0.0000

Data Index: 1631955 (Python Code)

Max Activating Token Index: 484

Text #9

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.2375. Min Act: -0.0000

Data Index: 1551888 (Python Code)

Max Activating Token Index: 817

Text #10

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.2530. Min Act: -0.0000

Data Index: 1591089 (Python Code)

Max Activating Token Index: 496

Text #11

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.5511. Min Act: -0.0000

Data Index: 1374149 (Python Code)

Max Activating Token Index: 228

Text #12

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.3265. Min Act: -0.0000

Data Index: 1422551 (Python Code)

Max Activating Token Index: 702

Text #13

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.2713. Min Act: -0.0000

Data Index: 1541342 (Python Code)

Max Activating Token Index: 653

Text #14

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.2496. Min Act: -0.0000

Data Index: 1517260 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.3980. Min Act: -0.0000

Data Index: 1373279 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.1233. Min Act: -0.0000

Data Index: 1551700 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.1022. Min Act: -0.0000

Data Index: 1550483 (Python Code)

Max Activating Token Index: 667

Text #18

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.0901. Min Act: -0.0000

Data Index: 1582086 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 5.0253. Min Range: -5.0253

Max Act: 4.0709. Min Act: -0.0000

Data Index: 1461301 (Python Code)

Max Activating Token Index: 15