Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5973 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2677. Min Range: -5.2677

Max Act: 5.2677. Min Act: -0.0000

Data Index: 692046 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 5.2677. Min Range: -5.2677

Max Act: 4.9035. Min Act: -0.0000

Data Index: 901618 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 5.2677. Min Range: -5.2677

Max Act: 4.5849. Min Act: -0.0000

Data Index: 360135 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 5.2677. Min Range: -5.2677

Max Act: 5.0367. Min Act: -0.0000

Data Index: 595317 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 5.2677. Min Range: -5.2677

Max Act: 4.1746. Min Act: -0.0000

Data Index: 464792 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 5.2677. Min Range: -5.2677

Max Act: 4.2130. Min Act: -0.0000

Data Index: 1107305 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 5.2677. Min Range: -5.2677

Max Act: 4.0127. Min Act: -0.0000

Data Index: 1119517 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.9092. Min Act: -0.0000

Data Index: 280462 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.5877. Min Act: -0.0000

Data Index: 24238 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.9007. Min Act: -0.0000

Data Index: 635135 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.4802. Min Act: -0.0000

Data Index: 121889 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.4866. Min Act: -0.0000

Data Index: 1193078 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.1856. Min Act: -0.0000

Data Index: 1336878 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.3467. Min Act: -0.0000

Data Index: 452433 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.2620. Min Act: -0.0000

Data Index: 257949 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.3980. Min Act: -0.0000

Data Index: 239420 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.2174. Min Act: -0.0000

Data Index: 1053355 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.1904. Min Act: -0.0000

Data Index: 1288593 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.1976. Min Act: -0.0000

Data Index: 942473 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 5.2677. Min Range: -5.2677

Max Act: 3.1839. Min Act: -0.0000

Data Index: 550036 (C4 (Web Text))

Max Activating Token Index: 535