Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3213 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2960. Min Act: -0.0001

Data Index: 271702 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2529. Min Act: -0.0000

Data Index: 290641 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2553. Min Act: -0.0000

Data Index: 553308 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2478. Min Act: -0.0000

Data Index: 166952 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2185. Min Act: -0.0000

Data Index: 836841 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2256. Min Act: -0.0000

Data Index: 966968 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1773. Min Act: -0.0000

Data Index: 498299 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1887. Min Act: -0.0000

Data Index: 535447 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2106. Min Act: -0.0000

Data Index: 739134 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1989. Min Act: -0.0000

Data Index: 670455 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2018. Min Act: -0.0000

Data Index: 677651 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1050014 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1908. Min Act: -0.0001

Data Index: 222526 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1821. Min Act: -0.0000

Data Index: 798684 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1905. Min Act: -0.0000

Data Index: 351335 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1113285 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1994. Min Act: -0.0000

Data Index: 21360 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1027454 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1932. Min Act: -0.0000

Data Index: 612321 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.2960. Min Range: -0.2960

Max Act: 0.1918. Min Act: -0.0000

Data Index: 645805 (C4 (Web Text))

Max Activating Token Index: 755