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

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

Neuron 1013 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: 1.5878. Min Range: -1.5878

Max Act: 1.5878. Min Act: -0.0002

Data Index: 784122 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.4831. Min Act: -0.0002

Data Index: 352104 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.4222. Min Act: -0.0002

Data Index: 516693 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3124. Min Act: -0.0001

Data Index: 649113 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.3121. Min Act: -0.0002

Data Index: 584613 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.2674. Min Act: -0.0002

Data Index: 1042808 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.2735. Min Act: -0.0001

Data Index: 315492 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.2328. Min Act: -0.0002

Data Index: 1025482 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1602. Min Act: -0.0002

Data Index: 282724 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0495. Min Act: -0.0002

Data Index: 741150 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1154. Min Act: -0.0001

Data Index: 615066 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0770. Min Act: -0.0002

Data Index: 306961 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1151. Min Act: -0.0001

Data Index: 111115 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0532. Min Act: -0.0002

Data Index: 1129830 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0900. Min Act: -0.0001

Data Index: 1033077 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.1165. Min Act: -0.0002

Data Index: 538208 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0623. Min Act: -0.0002

Data Index: 219439 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.5878. Min Range: -1.5878

Max Act: 0.9329. Min Act: -0.0002

Data Index: 250481 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0126. Min Act: -0.0002

Data Index: 837930 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.5878. Min Range: -1.5878

Max Act: 1.0372. Min Act: -0.0002

Data Index: 808989 (C4 (Web Text))

Max Activating Token Index: 553