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

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

Neuron 5735 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: 0.3302. Min Range: -0.3302

Max Act: 0.3302. Min Act: -0.0000

Data Index: 244787 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1335430 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2214. Min Act: -0.0000

Data Index: 374098 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2121. Min Act: -0.0000

Data Index: 716844 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1033830 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1241108 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1198403 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2004. Min Act: -0.0000

Data Index: 781848 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1824. Min Act: -0.0000

Data Index: 878260 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2219. Min Act: -0.0000

Data Index: 67406 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1978. Min Act: -0.0000

Data Index: 971480 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1916. Min Act: -0.0000

Data Index: 486978 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1920. Min Act: -0.0000

Data Index: 128058 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1734. Min Act: -0.0000

Data Index: 506645 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1329054 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1020837 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1740. Min Act: -0.0000

Data Index: 888172 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1788. Min Act: -0.0000

Data Index: 831314 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1891. Min Act: -0.0000

Data Index: 801476 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1002405 (C4 (Web Text))

Max Activating Token Index: 62