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

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

Neuron 795 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5806. Min Range: -1.5806

Max Act: 1.5806. Min Act: -0.0000

Data Index: 1518737 (Python Code)

Max Activating Token Index: 526

Text #1

Max Range: 1.5806. Min Range: -1.5806

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1402323 (Python Code)

Max Activating Token Index: 480

Text #2

Max Range: 1.5806. Min Range: -1.5806

Max Act: 1.2086. Min Act: -0.0000

Data Index: 1624986 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 1.5806. Min Range: -1.5806

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1516232 (Python Code)

Max Activating Token Index: 320

Text #4

Max Range: 1.5806. Min Range: -1.5806

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1648035 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 1.5806. Min Range: -1.5806

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1612092 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 1.5806. Min Range: -1.5806

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1578445 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 1.5806. Min Range: -1.5806

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1417771 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1377136 (Python Code)

Max Activating Token Index: 324

Text #9

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.9033. Min Act: -0.0000

Data Index: 1540942 (Python Code)

Max Activating Token Index: 383

Text #10

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1368247 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1444620 (Python Code)

Max Activating Token Index: 774

Text #12

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.9578. Min Act: -0.0000

Data Index: 1487771 (Python Code)

Max Activating Token Index: 820

Text #13

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1512328 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1637209 (Python Code)

Max Activating Token Index: 744

Text #15

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1533565 (Python Code)

Max Activating Token Index: 665

Text #16

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1629530 (Python Code)

Max Activating Token Index: 438

Text #17

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1499038 (Python Code)

Max Activating Token Index: 646

Text #18

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1642158 (Python Code)

Max Activating Token Index: 780

Text #19

Max Range: 1.5806. Min Range: -1.5806

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1651270 (Python Code)

Max Activating Token Index: 206