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

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

Neuron 4334 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0814. Min Range: -1.0814

Max Act: 1.0814. Min Act: -0.0000

Data Index: 889485 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.9944. Min Act: -0.0000

Data Index: 170264 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.9572. Min Act: -0.0000

Data Index: 781115 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1558485 (Python Code)

Max Activating Token Index: 660

Text #4

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.8910. Min Act: -0.0000

Data Index: 789521 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.9360. Min Act: -0.0000

Data Index: 413183 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.8463. Min Act: -0.0000

Data Index: 1039800 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.8398. Min Act: -0.0000

Data Index: 297430 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1302533 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1141181 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7974. Min Act: -0.0000

Data Index: 206719 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7513. Min Act: -0.0000

Data Index: 275197 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.8166. Min Act: -0.0000

Data Index: 1207327 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7867. Min Act: -0.0000

Data Index: 60048 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1373500 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1103034 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1515376 (Python Code)

Max Activating Token Index: 1017

Text #17

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1240296 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7093. Min Act: -0.0000

Data Index: 20060 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 1.0814. Min Range: -1.0814

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1327360 (C4 (Web Text))

Max Activating Token Index: 242