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

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

Neuron 3015 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0171. Min Range: -4.0171

Max Act: 4.0171. Min Act: -0.0000

Data Index: 88756 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.5846. Min Act: -0.0000

Data Index: 1469673 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.3368. Min Act: -0.0000

Data Index: 1196559 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.6656. Min Act: -0.0000

Data Index: 1515282 (Python Code)

Max Activating Token Index: 926

Text #4

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.4439. Min Act: -0.0000

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.1422. Min Act: -0.0000

Data Index: 1263459 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.4246. Min Act: -0.0000

Data Index: 742697 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.4108. Min Act: -0.0000

Data Index: 1589082 (Python Code)

Max Activating Token Index: 412

Text #8

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.2744. Min Act: -0.0000

Data Index: 1552473 (Python Code)

Max Activating Token Index: 239

Text #9

Max Range: 4.0171. Min Range: -4.0171

Max Act: 2.8305. Min Act: -0.0000

Data Index: 1244014 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.0866. Min Act: -0.0000

Data Index: 1309977 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.1996. Min Act: -0.0000

Data Index: 952051 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 4.0171. Min Range: -4.0171

Max Act: 2.7824. Min Act: -0.0000

Data Index: 632293 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.0383. Min Act: -0.0000

Data Index: 967261 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.0417. Min Act: -0.0000

Data Index: 1385238 (Python Code)

Max Activating Token Index: 961

Text #15

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.1729. Min Act: -0.0000

Data Index: 1110113 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 4.0171. Min Range: -4.0171

Max Act: 3.0069. Min Act: -0.0000

Data Index: 452986 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 4.0171. Min Range: -4.0171

Max Act: 2.6709. Min Act: -0.0000

Data Index: 172460 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 4.0171. Min Range: -4.0171

Max Act: 2.9455. Min Act: -0.0000

Data Index: 1491466 (Python Code)

Max Activating Token Index: 705

Text #19

Max Range: 4.0171. Min Range: -4.0171

Max Act: 2.6574. Min Act: -0.0000

Data Index: 122109 (C4 (Web Text))

Max Activating Token Index: 922