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

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

Neuron 1977 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.9577. Min Act: -0.0000

Data Index: 1544289 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.7469. Min Act: -0.0000

Data Index: 1415495 (Python Code)

Max Activating Token Index: 648

Text #2

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.5299. Min Act: -0.0000

Data Index: 1599392 (Python Code)

Max Activating Token Index: 715

Text #3

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.7194. Min Act: -0.0000

Data Index: 1586126 (Python Code)

Max Activating Token Index: 954

Text #4

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.6616. Min Act: -0.0000

Data Index: 1382844 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.5056. Min Act: -0.0000

Data Index: 1407859 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.6883. Min Act: -0.0000

Data Index: 1419262 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.4883. Min Act: -0.0000

Data Index: 1649527 (Python Code)

Max Activating Token Index: 938

Text #8

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.3033. Min Act: -0.0000

Data Index: 1444497 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.3936. Min Act: -0.0000

Data Index: 1644105 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.3551. Min Act: -0.0000

Data Index: 1400207 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.3748. Min Act: -0.0000

Data Index: 1541371 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.1695. Min Act: -0.0000

Data Index: 1617457 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.3336. Min Act: -0.0000

Data Index: 1378327 (Python Code)

Max Activating Token Index: 639

Text #14

Max Range: 2.9577. Min Range: -2.9577

Max Act: 1.8873. Min Act: -0.0001

Data Index: 1519142 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.1882. Min Act: -0.0000

Data Index: 1379674 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.1647. Min Act: -0.0000

Data Index: 1530908 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.1384. Min Act: -0.0001

Data Index: 1472092 (Python Code)

Max Activating Token Index: 514

Text #18

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.0890. Min Act: -0.0001

Data Index: 1454110 (Python Code)

Max Activating Token Index: 20

Text #19

Max Range: 2.9577. Min Range: -2.9577

Max Act: 2.1609. Min Act: -0.0000

Data Index: 1524027 (Python Code)

Max Activating Token Index: 459