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

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

Neuron 1740 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.5692. Min Act: -0.0001

Data Index: 401807 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.5773. Min Act: -0.0001

Data Index: 535811 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1076761 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.5112. Min Act: -0.0001

Data Index: 266256 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4747. Min Act: -0.0001

Data Index: 618165 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.5040. Min Act: -0.0001

Data Index: 1090932 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4832. Min Act: -0.0001

Data Index: 492861 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4269. Min Act: -0.0001

Data Index: 763090 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4954. Min Act: -0.0001

Data Index: 610586 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4442. Min Act: -0.0001

Data Index: 1328708 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4660. Min Act: -0.0001

Data Index: 649958 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4297. Min Act: -0.0001

Data Index: 276111 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4073. Min Act: -0.0001

Data Index: 1225214 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3646. Min Act: -0.0001

Data Index: 573425 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3871. Min Act: -0.0001

Data Index: 1000353 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.4005. Min Act: -0.0001

Data Index: 924438 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3926. Min Act: -0.0001

Data Index: 839765 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3558. Min Act: -0.0002

Data Index: 984802 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3888. Min Act: -0.0001

Data Index: 1328426 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 0.5773. Min Range: -0.5773

Max Act: 0.3877. Min Act: -0.0001

Data Index: 723042 (C4 (Web Text))

Max Activating Token Index: 600