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

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

Neuron 2142 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1072. Min Range: -3.1072

Max Act: 3.1072. Min Act: -0.0000

Data Index: 262411 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.7476. Min Act: -0.0000

Data Index: 1305069 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.7755. Min Act: -0.0000

Data Index: 419492 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.5825. Min Act: -0.0000

Data Index: 773448 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.3735. Min Act: -0.0000

Data Index: 439995 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.3558. Min Act: -0.0000

Data Index: 472680 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.2881. Min Act: -0.0000

Data Index: 1024137 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.2472. Min Act: -0.0000

Data Index: 1154829 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.2627. Min Act: -0.0000

Data Index: 1122808 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.2362. Min Act: -0.0000

Data Index: 1253294 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.1975. Min Act: -0.0000

Data Index: 315930 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.2862. Min Act: -0.0000

Data Index: 1122816 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.1500. Min Act: -0.0000

Data Index: 273262 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.0268. Min Act: -0.0000

Data Index: 642840 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.0931. Min Act: -0.0000

Data Index: 1345317 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 3.1072. Min Range: -3.1072

Max Act: 1.9739. Min Act: -0.0000

Data Index: 1322213 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.1002. Min Act: -0.0000

Data Index: 374333 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.0777. Min Act: -0.0000

Data Index: 1175940 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 3.1072. Min Range: -3.1072

Max Act: 2.1723. Min Act: -0.0000

Data Index: 1052143 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 3.1072. Min Range: -3.1072

Max Act: 1.9394. Min Act: -0.0000

Data Index: 1194348 (C4 (Web Text))

Max Activating Token Index: 428