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

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

Neuron 1344 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0116. Min Range: -4.0116

Max Act: 4.0116. Min Act: -0.0000

Data Index: 215863 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.8917. Min Act: -0.0000

Data Index: 176515 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.1389. Min Act: -0.0000

Data Index: 1058345 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.8418. Min Act: -0.0000

Data Index: 660399 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.2313. Min Act: -0.0000

Data Index: 1329392 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 4.0116. Min Range: -4.0116

Max Act: 3.3573. Min Act: -0.0000

Data Index: 145382 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.8079. Min Act: -0.0000

Data Index: 1177206 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.9721. Min Act: -0.0000

Data Index: 1644873 (Python Code)

Max Activating Token Index: 895

Text #8

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.2769. Min Act: -0.0000

Data Index: 1603625 (Python Code)

Max Activating Token Index: 816

Text #9

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.2904. Min Act: -0.0000

Data Index: 507444 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.5241. Min Act: -0.0000

Data Index: 1165107 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.3656. Min Act: -0.0000

Data Index: 1479087 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.4404. Min Act: -0.0000

Data Index: 1400009 (Python Code)

Max Activating Token Index: 284

Text #13

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.3756. Min Act: -0.0000

Data Index: 1528172 (Python Code)

Max Activating Token Index: 253

Text #14

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.1075. Min Act: -0.0000

Data Index: 1380156 (Python Code)

Max Activating Token Index: 873

Text #15

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.2041. Min Act: -0.0000

Data Index: 394422 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.2307. Min Act: -0.0000

Data Index: 1360281 (Python Code)

Max Activating Token Index: 612

Text #17

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.1295. Min Act: -0.0000

Data Index: 901670 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.1045. Min Act: -0.0000

Data Index: 1423353 (Python Code)

Max Activating Token Index: 230

Text #19

Max Range: 4.0116. Min Range: -4.0116

Max Act: 2.2425. Min Act: -0.0000

Data Index: 1573138 (Python Code)

Max Activating Token Index: 799