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

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

Neuron 3309 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.4934. Min Act: -0.0000

Data Index: 1039240 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.4619. Min Act: -0.0000

Data Index: 1317097 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.4975. Min Act: -0.0000

Data Index: 1483749 (Python Code)

Max Activating Token Index: 833

Text #3

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.3243. Min Act: -0.0000

Data Index: 1628539 (Python Code)

Max Activating Token Index: 261

Text #4

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.3866. Min Act: -0.0000

Data Index: 1541839 (Python Code)

Max Activating Token Index: 193

Text #5

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.3809. Min Act: -0.0000

Data Index: 171276 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.1908. Min Act: -0.0000

Data Index: 1655796 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.2080. Min Act: -0.0000

Data Index: 1258769 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.1599. Min Act: -0.0000

Data Index: 1580983 (Python Code)

Max Activating Token Index: 1022

Text #9

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.9090. Min Act: -0.0000

Data Index: 1523600 (Python Code)

Max Activating Token Index: 224

Text #10

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.1037. Min Act: -0.0000

Data Index: 1421828 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.0961. Min Act: -0.0000

Data Index: 1651288 (Python Code)

Max Activating Token Index: 475

Text #12

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.9815. Min Act: -0.0000

Data Index: 1392816 (Python Code)

Max Activating Token Index: 687

Text #13

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.9713. Min Act: -0.0000

Data Index: 1373593 (Python Code)

Max Activating Token Index: 753

Text #14

Max Range: 2.4975. Min Range: -2.4975

Max Act: 1.9689. Min Act: -0.0000

Data Index: 1362993 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.0790. Min Act: -0.0000

Data Index: 1494176 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.1892. Min Act: -0.0000

Data Index: 435492 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.0595. Min Act: -0.0000

Data Index: 1443306 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.0570. Min Act: -0.0000

Data Index: 1549887 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 2.4975. Min Range: -2.4975

Max Act: 2.0542. Min Act: -0.0000

Data Index: 1635686 (Python Code)

Max Activating Token Index: 296