Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 801 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.3214. Min Act: -0.0000

Data Index: 1651009 (Python Code)

Max Activating Token Index: 835

Text #1

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1542795 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.1631. Min Act: -0.0000

Data Index: 1400058 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1434109 (Python Code)

Max Activating Token Index: 998

Text #4

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1586956 (Python Code)

Max Activating Token Index: 1009

Text #5

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1502423 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.0975. Min Act: 0.0002

Data Index: 1539589 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 1.3214. Min Range: -1.3214

Max Act: 1.0849. Min Act: -0.0000

Data Index: 1522027 (Python Code)

Max Activating Token Index: 83

Text #8

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1587121 (Python Code)

Max Activating Token Index: 841

Text #9

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9481. Min Act: -0.0000

Data Index: 1459513 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1536803 (Python Code)

Max Activating Token Index: 482

Text #11

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9244. Min Act: 0.0001

Data Index: 1572102 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1548788 (Python Code)

Max Activating Token Index: 147

Text #13

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1656329 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1462169 (Python Code)

Max Activating Token Index: 776

Text #15

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1441248 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8681. Min Act: -0.0000

Data Index: 1586247 (Python Code)

Max Activating Token Index: 402

Text #17

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1595510 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1373702 (Python Code)

Max Activating Token Index: 443

Text #19

Max Range: 1.3214. Min Range: -1.3214

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1525728 (Python Code)

Max Activating Token Index: 577