Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1606 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.1367. Min Act: -0.0001

Data Index: 1575454 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1455494 (Python Code)

Max Activating Token Index: 710

Text #2

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0988. Min Act: -0.0001

Data Index: 1382566 (Python Code)

Max Activating Token Index: 127

Text #3

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.1022. Min Act: -0.0001

Data Index: 1499706 (Python Code)

Max Activating Token Index: 116

Text #4

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.1575. Min Act: -0.0001

Data Index: 1611350 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0760. Min Act: -0.0001

Data Index: 1640039 (Python Code)

Max Activating Token Index: 357

Text #6

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0683. Min Act: -0.0001

Data Index: 1389524 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0307. Min Act: -0.0001

Data Index: 1563304 (Python Code)

Max Activating Token Index: 165

Text #8

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.1373. Min Act: -0.0001

Data Index: 1448406 (Python Code)

Max Activating Token Index: 68

Text #9

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0717. Min Act: -0.0001

Data Index: 1618471 (Python Code)

Max Activating Token Index: 202

Text #10

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0247. Min Act: -0.0001

Data Index: 1605109 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0205. Min Act: -0.0001

Data Index: 1563218 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9575. Min Act: -0.0001

Data Index: 1454476 (Python Code)

Max Activating Token Index: 852

Text #13

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0104. Min Act: -0.0001

Data Index: 1416229 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1533708 (Python Code)

Max Activating Token Index: 38

Text #15

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0043. Min Act: -0.0001

Data Index: 1408241 (Python Code)

Max Activating Token Index: 351

Text #16

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9736. Min Act: -0.0001

Data Index: 1459074 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1646683 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1509038 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1542929 (Python Code)

Max Activating Token Index: 954