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

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

Neuron 3328 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.6037. Min Act: -0.0001

Data Index: 1111354 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5547. Min Act: -0.0001

Data Index: 125924 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5795. Min Act: -0.0001

Data Index: 606651 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5610. Min Act: -0.0001

Data Index: 349629 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5035. Min Act: -0.0001

Data Index: 335292 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5366. Min Act: -0.0001

Data Index: 1128118 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5035. Min Act: -0.0001

Data Index: 876650 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5182. Min Act: -0.0001

Data Index: 1104772 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5329. Min Act: -0.0001

Data Index: 293245 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5504. Min Act: -0.0001

Data Index: 605833 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5295. Min Act: -0.0001

Data Index: 981900 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5095. Min Act: -0.0001

Data Index: 767662 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5062. Min Act: -0.0001

Data Index: 414866 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5048. Min Act: -0.0001

Data Index: 979045 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5148. Min Act: -0.0001

Data Index: 322858 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5158. Min Act: -0.0001

Data Index: 213449 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4816. Min Act: -0.0001

Data Index: 123892 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5061. Min Act: -0.0001

Data Index: 211293 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5058. Min Act: -0.0001

Data Index: 1129242 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4857. Min Act: -0.0001

Data Index: 1008391 (C4 (Web Text))

Max Activating Token Index: 367