Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4614 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2760. Min Act: -0.0001

Data Index: 441015 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2796. Min Act: -0.0001

Data Index: 1206923 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2482. Min Act: -0.0001

Data Index: 755125 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2190. Min Act: -0.0001

Data Index: 716452 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1976. Min Act: -0.0001

Data Index: 735084 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1062694 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1854. Min Act: -0.0001

Data Index: 528606 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2039. Min Act: -0.0001

Data Index: 811335 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1891. Min Act: -0.0001

Data Index: 407359 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2030. Min Act: -0.0001

Data Index: 324676 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1996. Min Act: -0.0001

Data Index: 333228 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1917. Min Act: -0.0001

Data Index: 792940 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1937. Min Act: -0.0001

Data Index: 596508 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1343307 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1923. Min Act: -0.0001

Data Index: 762927 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.2011. Min Act: -0.0001

Data Index: 1637873 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1981. Min Act: -0.0001

Data Index: 662769 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1977. Min Act: -0.0001

Data Index: 605439 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1973. Min Act: -0.0001

Data Index: 79065 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.2796. Min Range: -0.2796

Max Act: 0.1879. Min Act: -0.0001

Data Index: 774525 (C4 (Web Text))

Max Activating Token Index: 752