Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1155 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.5117. Min Act: -0.0002

Data Index: 50148 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4645. Min Act: -0.0001

Data Index: 1377378 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4773. Min Act: -0.0001

Data Index: 1456464 (Python Code)

Max Activating Token Index: 112

Text #3

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4525. Min Act: -0.0001

Data Index: 811940 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4592. Min Act: -0.0002

Data Index: 754807 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4657. Min Act: -0.0001

Data Index: 1524665 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4615. Min Act: -0.0001

Data Index: 1560580 (Python Code)

Max Activating Token Index: 615

Text #7

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4333. Min Act: -0.0002

Data Index: 573155 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4612. Min Act: -0.0001

Data Index: 1604896 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4788. Min Act: -0.0001

Data Index: 813341 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4701. Min Act: -0.0001

Data Index: 605371 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4599. Min Act: -0.0001

Data Index: 1616600 (Python Code)

Max Activating Token Index: 691

Text #12

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4529. Min Act: -0.0001

Data Index: 1484844 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4591. Min Act: -0.0002

Data Index: 1390365 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4630. Min Act: -0.0001

Data Index: 1458051 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1543894 (Python Code)

Max Activating Token Index: 98

Text #16

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4483. Min Act: -0.0002

Data Index: 343024 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4458. Min Act: -0.0001

Data Index: 1595865 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4276. Min Act: -0.0002

Data Index: 322872 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.5117. Min Range: -0.5117

Max Act: 0.4460. Min Act: -0.0001

Data Index: 1368243 (Python Code)

Max Activating Token Index: 470