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

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

Neuron 426 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: 0.4886. Min Range: -0.4886

Max Act: 0.4886. Min Act: -0.0001

Data Index: 66508 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4870. Min Act: -0.0001

Data Index: 308909 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4717. Min Act: -0.0001

Data Index: 690410 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4405. Min Act: -0.0001

Data Index: 1098781 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3878. Min Act: -0.0000

Data Index: 460830 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4756. Min Act: -0.0001

Data Index: 398282 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4192. Min Act: -0.0000

Data Index: 612708 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4126. Min Act: -0.0001

Data Index: 507016 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4290. Min Act: -0.0001

Data Index: 17159 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4116. Min Act: -0.0001

Data Index: 295469 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4085. Min Act: -0.0001

Data Index: 20077 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4259. Min Act: -0.0001

Data Index: 702022 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4163. Min Act: -0.0001

Data Index: 333652 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4274. Min Act: -0.0001

Data Index: 953915 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3979. Min Act: -0.0001

Data Index: 199112 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3992. Min Act: -0.0001

Data Index: 942104 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3712. Min Act: -0.0001

Data Index: 1149652 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3486. Min Act: -0.0001

Data Index: 611727 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.3760. Min Act: -0.0001

Data Index: 335010 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.4886. Min Range: -0.4886

Max Act: 0.4087. Min Act: -0.0001

Data Index: 983080 (C4 (Web Text))

Max Activating Token Index: 319