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

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

Neuron 6047 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1625. Min Range: -2.1625

Max Act: 2.1625. Min Act: -0.0000

Data Index: 1411982 (Python Code)

Max Activating Token Index: 667

Text #1

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.7304. Min Act: -0.0000

Data Index: 1499730 (Python Code)

Max Activating Token Index: 513

Text #2

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.7722. Min Act: -0.0000

Data Index: 1589283 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.6659. Min Act: -0.0000

Data Index: 173408 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.6318. Min Act: -0.0000

Data Index: 1540868 (Python Code)

Max Activating Token Index: 773

Text #5

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.9253. Min Act: -0.0000

Data Index: 1393102 (Python Code)

Max Activating Token Index: 280

Text #6

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1508772 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.3322. Min Act: -0.0000

Data Index: 1470037 (Python Code)

Max Activating Token Index: 443

Text #8

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.6216. Min Act: -0.0000

Data Index: 1120128 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1472839 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.7666. Min Act: -0.0000

Data Index: 1461011 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.4879. Min Act: -0.0000

Data Index: 1401222 (Python Code)

Max Activating Token Index: 827

Text #12

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.5689. Min Act: -0.0000

Data Index: 762843 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.5312. Min Act: -0.0000

Data Index: 892574 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.5298. Min Act: -0.0000

Data Index: 1349265 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.5299. Min Act: -0.0000

Data Index: 1276271 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1475141 (Python Code)

Max Activating Token Index: 546

Text #17

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.6119. Min Act: -0.0000

Data Index: 1554217 (Python Code)

Max Activating Token Index: 398

Text #18

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.4032. Min Act: -0.0000

Data Index: 1459119 (Python Code)

Max Activating Token Index: 578

Text #19

Max Range: 2.1625. Min Range: -2.1625

Max Act: 1.4972. Min Act: -0.0000

Data Index: 1607771 (Python Code)

Max Activating Token Index: 725