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

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

Neuron 5870 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: 1.2527. Min Range: -1.2527

Max Act: 1.2276. Min Act: 0.0000

Data Index: 1428702 (Python Code)

Max Activating Token Index: 127

Text #1

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1584651 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.1639. Min Act: 0.0000

Data Index: 1625121 (Python Code)

Max Activating Token Index: 323

Text #3

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.1963. Min Act: 0.0000

Data Index: 1371271 (Python Code)

Max Activating Token Index: 103

Text #4

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.2463. Min Act: 0.0000

Data Index: 1475776 (Python Code)

Max Activating Token Index: 412

Text #5

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1419918 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.0778. Min Act: 0.0000

Data Index: 1596501 (Python Code)

Max Activating Token Index: 123

Text #7

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.1060. Min Act: 0.0000

Data Index: 1437201 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.0896. Min Act: 0.0000

Data Index: 1372982 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1565474 (Python Code)

Max Activating Token Index: 514

Text #10

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.1338. Min Act: 0.0000

Data Index: 1502805 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.0549. Min Act: 0.0000

Data Index: 1400150 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1548478 (Python Code)

Max Activating Token Index: 816

Text #13

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.0170. Min Act: 0.0000

Data Index: 1478303 (Python Code)

Max Activating Token Index: 969

Text #14

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.0270. Min Act: 0.0000

Data Index: 1505041 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 1.2527. Min Range: -1.2527

Max Act: 0.9293. Min Act: -0.0000

Data Index: 1650681 (Python Code)

Max Activating Token Index: 101

Text #16

Max Range: 1.2527. Min Range: -1.2527

Max Act: 0.9309. Min Act: 0.0000

Data Index: 1542989 (Python Code)

Max Activating Token Index: 994

Text #17

Max Range: 1.2527. Min Range: -1.2527

Max Act: 1.0204. Min Act: 0.0000

Data Index: 1586511 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 1.2527. Min Range: -1.2527

Max Act: 0.9254. Min Act: 0.0000

Data Index: 1474809 (Python Code)

Max Activating Token Index: 103

Text #19

Max Range: 1.2527. Min Range: -1.2527

Max Act: 0.9307. Min Act: 0.0000

Data Index: 1478186 (Python Code)

Max Activating Token Index: 683