Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 633 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.4691. Min Act: -0.0003

Data Index: 955248 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.4442. Min Act: -0.0004

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.3671. Min Act: -0.0003

Data Index: 874755 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.3379. Min Act: -0.0003

Data Index: 654027 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.3144. Min Act: -0.0003

Data Index: 829026 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.3194. Min Act: -0.0003

Data Index: 1092392 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.3042. Min Act: -0.0003

Data Index: 399303 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.3031. Min Act: -0.0003

Data Index: 1140580 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2936. Min Act: -0.0003

Data Index: 380521 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.3221. Min Act: -0.0003

Data Index: 343154 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2837. Min Act: -0.0003

Data Index: 515342 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2913. Min Act: -0.0003

Data Index: 640849 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2783. Min Act: -0.0003

Data Index: 930037 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2765. Min Act: -0.0003

Data Index: 390112 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2738. Min Act: -0.0003

Data Index: 997287 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2662. Min Act: -0.0003

Data Index: 682313 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2467. Min Act: -0.0003

Data Index: 942447 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2468. Min Act: -0.0003

Data Index: 1059305 (C4 (Web Text))

Max Activating Token Index: 558

Text #18

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2301. Min Act: -0.0003

Data Index: 220356 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.4691. Min Range: -0.4691

Max Act: 0.2351. Min Act: -0.0003

Data Index: 1065755 (C4 (Web Text))

Max Activating Token Index: 762