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

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

Neuron 4557 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: 0.9178. Min Range: -0.9178

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1426249 (Python Code)

Max Activating Token Index: 405

Text #1

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1364475 (Python Code)

Max Activating Token Index: 576

Text #2

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1473164 (Python Code)

Max Activating Token Index: 798

Text #3

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1385131 (Python Code)

Max Activating Token Index: 624

Text #4

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1367291 (Python Code)

Max Activating Token Index: 244

Text #5

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1382857 (Python Code)

Max Activating Token Index: 68

Text #6

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1556376 (Python Code)

Max Activating Token Index: 305

Text #7

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1483850 (Python Code)

Max Activating Token Index: 782

Text #8

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1549877 (Python Code)

Max Activating Token Index: 995

Text #9

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1613187 (Python Code)

Max Activating Token Index: 64

Text #10

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1493399 (Python Code)

Max Activating Token Index: 78

Text #11

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1416027 (Python Code)

Max Activating Token Index: 653

Text #12

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1404997 (Python Code)

Max Activating Token Index: 96

Text #13

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1587064 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1362761 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1594742 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1567843 (Python Code)

Max Activating Token Index: 386

Text #17

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.7270. Min Act: -0.0000

Data Index: 1478109 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1393917 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 0.9178. Min Range: -0.9178

Max Act: 0.6949. Min Act: -0.0000

Data Index: 1553298 (Python Code)

Max Activating Token Index: 520