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

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

Neuron 1953 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: 2.6628. Min Range: -2.6628

Max Act: 2.6628. Min Act: -0.0000

Data Index: 880561 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.4418. Min Act: -0.0000

Data Index: 1179851 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.5156. Min Act: -0.0000

Data Index: 880670 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.2508. Min Act: -0.0000

Data Index: 216375 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.3848. Min Act: -0.0000

Data Index: 634164 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.2435. Min Act: -0.0000

Data Index: 296983 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.2478. Min Act: -0.0000

Data Index: 323805 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.1936. Min Act: -0.0000

Data Index: 1091263 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0061. Min Act: -0.0000

Data Index: 292444 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0974. Min Act: -0.0000

Data Index: 985069 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0645. Min Act: -0.0000

Data Index: 1037607 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0317. Min Act: -0.0000

Data Index: 1323555 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.1305. Min Act: -0.0000

Data Index: 423272 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 2.6628. Min Range: -2.6628

Max Act: 1.8893. Min Act: -0.0000

Data Index: 585301 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 2.6628. Min Range: -2.6628

Max Act: 2.0122. Min Act: -0.0000

Data Index: 629938 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 2.6628. Min Range: -2.6628

Max Act: 1.9646. Min Act: -0.0000

Data Index: 265703 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 2.6628. Min Range: -2.6628

Max Act: 1.9745. Min Act: -0.0000

Data Index: 694049 (C4 (Web Text))

Max Activating Token Index: 473

Text #17

Max Range: 2.6628. Min Range: -2.6628

Max Act: 1.8508. Min Act: -0.0000

Data Index: 427768 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 2.6628. Min Range: -2.6628

Max Act: 1.9404. Min Act: -0.0000

Data Index: 611979 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 2.6628. Min Range: -2.6628

Max Act: 1.8305. Min Act: -0.0000

Data Index: 623034 (C4 (Web Text))

Max Activating Token Index: 358