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

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

Neuron 3968 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: 0.6040. Min Range: -0.6040

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1532845 (Python Code)

Max Activating Token Index: 367

Text #1

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1511528 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1632077 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1430897 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1383396 (Python Code)

Max Activating Token Index: 550

Text #5

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1552461 (Python Code)

Max Activating Token Index: 779

Text #6

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1639030 (Python Code)

Max Activating Token Index: 202

Text #7

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1577741 (Python Code)

Max Activating Token Index: 631

Text #8

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1386363 (Python Code)

Max Activating Token Index: 825

Text #9

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4931. Min Act: -0.0000

Data Index: 1542774 (Python Code)

Max Activating Token Index: 170

Text #10

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1570817 (Python Code)

Max Activating Token Index: 829

Text #11

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1627555 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4732. Min Act: -0.0000

Data Index: 1599481 (Python Code)

Max Activating Token Index: 738

Text #13

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1379340 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1594844 (Python Code)

Max Activating Token Index: 44

Text #15

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1497872 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1495903 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1501926 (Python Code)

Max Activating Token Index: 736

Text #18

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1634186 (Python Code)

Max Activating Token Index: 574

Text #19

Max Range: 0.6040. Min Range: -0.6040

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1581413 (Python Code)

Max Activating Token Index: 341