Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1768 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4971. Min Act: -0.0000

Data Index: 220365 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4682. Min Act: -0.0000

Data Index: 393293 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1333963 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4700. Min Act: -0.0000

Data Index: 430101 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1254245 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4343. Min Act: -0.0001

Data Index: 86802 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4208. Min Act: -0.0000

Data Index: 898336 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4226. Min Act: -0.0001

Data Index: 759948 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.3939. Min Act: -0.0001

Data Index: 17635 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4060. Min Act: -0.0000

Data Index: 481313 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4147. Min Act: -0.0001

Data Index: 699514 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4129. Min Act: -0.0000

Data Index: 577784 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4273. Min Act: -0.0000

Data Index: 237572 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4151. Min Act: -0.0000

Data Index: 415012 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4236. Min Act: -0.0000

Data Index: 496018 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1121158 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1161670 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4019. Min Act: -0.0001

Data Index: 585494 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1103660 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.4971. Min Range: -0.4971

Max Act: 0.4021. Min Act: -0.0000

Data Index: 869819 (C4 (Web Text))

Max Activating Token Index: 744