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

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

Neuron 15 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: 0.6000. Min Range: -0.6000

Max Act: 0.6000. Min Act: -0.0000

Data Index: 939481 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5268. Min Act: -0.0000

Data Index: 1280435 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5019. Min Act: -0.0000

Data Index: 987676 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1293343 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4608. Min Act: -0.0000

Data Index: 355604 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4481. Min Act: -0.0000

Data Index: 227900 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4464. Min Act: -0.0000

Data Index: 745532 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4266. Min Act: -0.0000

Data Index: 635823 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1292597 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1357087 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4160. Min Act: -0.0000

Data Index: 210366 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4174. Min Act: -0.0000

Data Index: 1243247 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1112752 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4148. Min Act: -0.0000

Data Index: 691386 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4112. Min Act: -0.0000

Data Index: 752055 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4227. Min Act: -0.0000

Data Index: 955311 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4046. Min Act: -0.0000

Data Index: 650072 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3931. Min Act: -0.0000

Data Index: 683466 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1142849 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4027. Min Act: -0.0000

Data Index: 484554 (C4 (Web Text))

Max Activating Token Index: 192