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

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

Neuron 3349 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.1125. Min Act: -0.0000

Data Index: 794715 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.0782. Min Act: -0.0000

Data Index: 377207 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.1003. Min Act: -0.0000

Data Index: 597174 (C4 (Web Text))

Max Activating Token Index: 468

Text #3

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.9835. Min Act: -0.0000

Data Index: 565398 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.1016. Min Act: -0.0000

Data Index: 891594 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 2.1125. Min Range: -2.1125

Max Act: 2.1046. Min Act: -0.0000

Data Index: 932150 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.7987. Min Act: -0.0000

Data Index: 1184363 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.9045. Min Act: -0.0000

Data Index: 17510 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8748. Min Act: -0.0000

Data Index: 1112249 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8415. Min Act: -0.0000

Data Index: 830892 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8613. Min Act: -0.0000

Data Index: 48908 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8297. Min Act: -0.0000

Data Index: 632919 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.6460. Min Act: -0.0001

Data Index: 136930 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8454. Min Act: -0.0000

Data Index: 1165168 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8009. Min Act: -0.0000

Data Index: 465990 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8874. Min Act: -0.0000

Data Index: 750877 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.6642. Min Act: -0.0000

Data Index: 889477 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.6672. Min Act: -0.0000

Data Index: 135622 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.6938. Min Act: -0.0000

Data Index: 1073882 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 2.1125. Min Range: -2.1125

Max Act: 1.8203. Min Act: -0.0000

Data Index: 1266745 (C4 (Web Text))

Max Activating Token Index: 956