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

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

Neuron 1121 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5061. Min Act: -0.0000

Data Index: 193550 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4859. Min Act: -0.0000

Data Index: 548149 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5268. Min Act: -0.0000

Data Index: 1619671 (Python Code)

Max Activating Token Index: 879

Text #3

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1405848 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1475127 (Python Code)

Max Activating Token Index: 1002

Text #5

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3884. Min Act: -0.0000

Data Index: 1524287 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5467. Min Act: -0.0000

Data Index: 1655672 (Python Code)

Max Activating Token Index: 910

Text #7

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4116. Min Act: -0.0000

Data Index: 1396022 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3401. Min Act: -0.0000

Data Index: 953801 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5158. Min Act: -0.0000

Data Index: 1369545 (Python Code)

Max Activating Token Index: 977

Text #10

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5972. Min Act: -0.0000

Data Index: 1522706 (Python Code)

Max Activating Token Index: 959

Text #11

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3151. Min Act: -0.0000

Data Index: 840377 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1485315 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1513325 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4136. Min Act: -0.0000

Data Index: 1645406 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1438749 (Python Code)

Max Activating Token Index: 213

Text #16

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3384. Min Act: -0.0000

Data Index: 1462435 (Python Code)

Max Activating Token Index: 910

Text #17

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1557967 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1370480 (Python Code)

Max Activating Token Index: 862

Text #19

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3682. Min Act: -0.0000

Data Index: 976737 (C4 (Web Text))

Max Activating Token Index: 97