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

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

Neuron 3164 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.4900. Min Act: -0.0000

Data Index: 627227 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.2947. Min Act: -0.0000

Data Index: 310177 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.2884. Min Act: -0.0000

Data Index: 427579 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.2677. Min Act: -0.0000

Data Index: 875903 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.2478. Min Act: -0.0000

Data Index: 1084958 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.1833. Min Act: -0.0000

Data Index: 805337 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.1759. Min Act: -0.0000

Data Index: 721484 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.3201. Min Act: -0.0000

Data Index: 826591 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.1438. Min Act: -0.0000

Data Index: 708452 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.1429. Min Act: -0.0000

Data Index: 1697 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.3275. Min Act: -0.0000

Data Index: 791070 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.0803. Min Act: -0.0000

Data Index: 794444 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.0551. Min Act: -0.0000

Data Index: 115285 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 4.4900. Min Range: -4.4900

Max Act: 3.9919. Min Act: -0.0000

Data Index: 214892 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 4.4900. Min Range: -4.4900

Max Act: 3.9863. Min Act: -0.0000

Data Index: 569844 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 4.4900. Min Range: -4.4900

Max Act: 3.9445. Min Act: -0.0000

Data Index: 980642 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 4.4900. Min Range: -4.4900

Max Act: 4.1394. Min Act: -0.0000

Data Index: 1235167 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 4.4900. Min Range: -4.4900

Max Act: 3.9572. Min Act: -0.0000

Data Index: 970846 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 4.4900. Min Range: -4.4900

Max Act: 3.9236. Min Act: -0.0000

Data Index: 1181478 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 4.4900. Min Range: -4.4900

Max Act: 3.8445. Min Act: -0.0000

Data Index: 511827 (C4 (Web Text))

Max Activating Token Index: 32