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

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

Neuron 533 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.1390. Min Act: -0.0000

Data Index: 402700 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1497043 (Python Code)

Max Activating Token Index: 210

Text #2

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1364656 (Python Code)

Max Activating Token Index: 523

Text #3

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9951. Min Act: -0.0000

Data Index: 1623479 (Python Code)

Max Activating Token Index: 498

Text #4

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1366393 (Python Code)

Max Activating Token Index: 202

Text #5

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1461917 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.0300. Min Act: -0.0000

Data Index: 538276 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1634770 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 1.1390. Min Range: -1.1390

Max Act: 1.0431. Min Act: -0.0000

Data Index: 1625217 (Python Code)

Max Activating Token Index: 607

Text #9

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9766. Min Act: -0.0000

Data Index: 1601401 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9453. Min Act: -0.0000

Data Index: 784739 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9572. Min Act: -0.0000

Data Index: 368980 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1261246 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1466072 (Python Code)

Max Activating Token Index: 834

Text #14

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.8660. Min Act: -0.0000

Data Index: 460619 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1610466 (Python Code)

Max Activating Token Index: 402

Text #16

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9246. Min Act: -0.0000

Data Index: 696788 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.8790. Min Act: -0.0000

Data Index: 658664 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1388984 (Python Code)

Max Activating Token Index: 448

Text #19

Max Range: 1.1390. Min Range: -1.1390

Max Act: 0.9336. Min Act: -0.0000

Data Index: 192616 (C4 (Web Text))

Max Activating Token Index: 987