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

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

Neuron 2133 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: 1.6746. Min Range: -1.6746

Max Act: 1.5128. Min Act: -0.0001

Data Index: 1591812 (Python Code)

Max Activating Token Index: 569

Text #1

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.6746. Min Act: -0.0001

Data Index: 1505857 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.5789. Min Act: -0.0001

Data Index: 1590082 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.5574. Min Act: -0.0001

Data Index: 1655439 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4721. Min Act: -0.0000

Data Index: 1442958 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.5271. Min Act: -0.0000

Data Index: 1573157 (Python Code)

Max Activating Token Index: 445

Text #6

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4628. Min Act: -0.0000

Data Index: 1424479 (Python Code)

Max Activating Token Index: 930

Text #7

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.5952. Min Act: -0.0001

Data Index: 1585920 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.5052. Min Act: -0.0001

Data Index: 404405 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4852. Min Act: -0.0001

Data Index: 1561545 (Python Code)

Max Activating Token Index: 638

Text #10

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.5627. Min Act: -0.0001

Data Index: 1558759 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4748. Min Act: -0.0001

Data Index: 1476233 (Python Code)

Max Activating Token Index: 122

Text #12

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4736. Min Act: -0.0000

Data Index: 1553274 (Python Code)

Max Activating Token Index: 242

Text #13

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.3821. Min Act: -0.0001

Data Index: 1474232 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1609100 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4477. Min Act: -0.0001

Data Index: 1431888 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4934. Min Act: -0.0001

Data Index: 1571481 (Python Code)

Max Activating Token Index: 508

Text #17

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4493. Min Act: -0.0001

Data Index: 1360847 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.4014. Min Act: -0.0001

Data Index: 1551979 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 1.6746. Min Range: -1.6746

Max Act: 1.3933. Min Act: -0.0001

Data Index: 1596195 (Python Code)

Max Activating Token Index: 162