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

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

Neuron 552 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.7260. Min Act: -0.0000

Data Index: 813673 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.6061. Min Act: -0.0000

Data Index: 726650 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1169220 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4922. Min Act: -0.0000

Data Index: 292448 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4888. Min Act: -0.0000

Data Index: 518980 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.5118. Min Act: -0.0000

Data Index: 609183 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4324. Min Act: -0.0000

Data Index: 30044 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4630. Min Act: -0.0000

Data Index: 241263 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4134. Min Act: -0.0000

Data Index: 33790 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4565. Min Act: -0.0000

Data Index: 346344 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1192203 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4428. Min Act: -0.0000

Data Index: 355118 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4742. Min Act: -0.0000

Data Index: 1339959 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4246. Min Act: -0.0000

Data Index: 418430 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4037. Min Act: -0.0000

Data Index: 768394 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4182. Min Act: -0.0000

Data Index: 746731 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4616. Min Act: -0.0000

Data Index: 11919 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.4027. Min Act: -0.0000

Data Index: 494266 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3615. Min Act: -0.0000

Data Index: 660739 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.7260. Min Range: -0.7260

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1188462 (C4 (Web Text))

Max Activating Token Index: 678