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

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

Neuron 4939 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: 2.2404. Min Range: -2.2404

Max Act: 2.2404. Min Act: -0.0000

Data Index: 1354483 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.8565. Min Act: -0.0000

Data Index: 184586 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.8772. Min Act: -0.0000

Data Index: 461922 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.5398. Min Act: -0.0000

Data Index: 839573 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.6206. Min Act: -0.0000

Data Index: 565820 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.5296. Min Act: -0.0000

Data Index: 919395 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.5079. Min Act: -0.0000

Data Index: 311516 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.4631. Min Act: -0.0000

Data Index: 15142 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.5560. Min Act: -0.0000

Data Index: 1162891 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.3555. Min Act: -0.0000

Data Index: 52348 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.4010. Min Act: -0.0000

Data Index: 37416 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.3110. Min Act: -0.0000

Data Index: 745258 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.3084. Min Act: -0.0000

Data Index: 675505 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.2963. Min Act: -0.0000

Data Index: 113269 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.2873. Min Act: -0.0000

Data Index: 589914 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1272925 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.1711. Min Act: -0.0000

Data Index: 565326 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.2289. Min Act: -0.0000

Data Index: 1035546 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.1664. Min Act: -0.0000

Data Index: 165181 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 2.2404. Min Range: -2.2404

Max Act: 1.2967. Min Act: -0.0000

Data Index: 637091 (C4 (Web Text))

Max Activating Token Index: 292