Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1536 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2900. Min Act: -0.0001

Data Index: 244636 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2453. Min Act: -0.0001

Data Index: 474138 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2180. Min Act: -0.0001

Data Index: 82364 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2045. Min Act: -0.0001

Data Index: 446356 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.2012. Min Act: -0.0001

Data Index: 739447 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1970. Min Act: -0.0001

Data Index: 336120 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1148269 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1944. Min Act: -0.0001

Data Index: 787222 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1014369 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1889. Min Act: -0.0001

Data Index: 773057 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1827. Min Act: -0.0001

Data Index: 521135 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1042516 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1794. Min Act: -0.0001

Data Index: 929486 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1723. Min Act: -0.0001

Data Index: 482066 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1676. Min Act: -0.0001

Data Index: 492335 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1725. Min Act: -0.0001

Data Index: 99994 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1675. Min Act: -0.0001

Data Index: 521860 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1833. Min Act: -0.0001

Data Index: 287984 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1772. Min Act: -0.0001

Data Index: 213933 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.2900. Min Range: -0.2900

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1175035 (C4 (Web Text))

Max Activating Token Index: 690