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

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

Neuron 1688 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0801. Min Range: -1.0801

Max Act: 1.0801. Min Act: -0.0001

Data Index: 157168 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8897. Min Act: -0.0001

Data Index: 600250 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8723. Min Act: -0.0001

Data Index: 1402147 (Python Code)

Max Activating Token Index: 1015

Text #3

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9630. Min Act: -0.0001

Data Index: 1649205 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9714. Min Act: -0.0001

Data Index: 1586137 (Python Code)

Max Activating Token Index: 994

Text #5

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8086. Min Act: -0.0001

Data Index: 1611913 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.9080. Min Act: -0.0001

Data Index: 1437856 (Python Code)

Max Activating Token Index: 275

Text #7

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8814. Min Act: -0.0001

Data Index: 1603959 (Python Code)

Max Activating Token Index: 991

Text #8

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8588. Min Act: -0.0001

Data Index: 1584912 (Python Code)

Max Activating Token Index: 374

Text #9

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.8149. Min Act: -0.0001

Data Index: 1644950 (Python Code)

Max Activating Token Index: 577

Text #10

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7830. Min Act: -0.0001

Data Index: 1590223 (Python Code)

Max Activating Token Index: 1014

Text #11

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7965. Min Act: -0.0001

Data Index: 657548 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7426. Min Act: -0.0001

Data Index: 1603583 (Python Code)

Max Activating Token Index: 477

Text #13

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7736. Min Act: -0.0001

Data Index: 1404727 (Python Code)

Max Activating Token Index: 900

Text #14

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7466. Min Act: -0.0001

Data Index: 1607969 (Python Code)

Max Activating Token Index: 1008

Text #15

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7571. Min Act: -0.0001

Data Index: 1488634 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.6878. Min Act: -0.0001

Data Index: 1484460 (Python Code)

Max Activating Token Index: 1002

Text #17

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1376535 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7535. Min Act: -0.0001

Data Index: 1442304 (Python Code)

Max Activating Token Index: 639

Text #19

Max Range: 1.0801. Min Range: -1.0801

Max Act: 0.7544. Min Act: -0.0001

Data Index: 1504709 (Python Code)

Max Activating Token Index: 297