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

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

Neuron 3726 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: 0.7035. Min Range: -0.7035

Max Act: 0.7035. Min Act: -0.0000

Data Index: 125199 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6363. Min Act: -0.0000

Data Index: 20641 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6591. Min Act: -0.0000

Data Index: 246761 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6477. Min Act: -0.0000

Data Index: 1270044 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.6185. Min Act: -0.0000

Data Index: 541850 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.5679. Min Act: -0.0000

Data Index: 501497 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4985. Min Act: -0.0000

Data Index: 640920 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.5337. Min Act: -0.0000

Data Index: 551692 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4514. Min Act: -0.0000

Data Index: 458001 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1107387 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4930. Min Act: -0.0000

Data Index: 100295 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1337634 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.5126. Min Act: -0.0000

Data Index: 98245 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4450. Min Act: -0.0000

Data Index: 432961 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4545. Min Act: -0.0000

Data Index: 477714 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4203. Min Act: -0.0000

Data Index: 397490 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4240. Min Act: -0.0000

Data Index: 947323 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1119179 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.4530. Min Act: -0.0000

Data Index: 132989 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.7035. Min Range: -0.7035

Max Act: 0.3827. Min Act: -0.0000

Data Index: 365176 (C4 (Web Text))

Max Activating Token Index: 869