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

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

Neuron 4397 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9940. Min Act: -0.0000

Data Index: 1417312 (Python Code)

Max Activating Token Index: 125

Text #1

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9421. Min Act: -0.0000

Data Index: 420279 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.1289. Min Act: -0.0000

Data Index: 487002 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.1289. Min Range: -1.1289

Max Act: 1.0034. Min Act: -0.0000

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9619. Min Act: -0.0000

Data Index: 479078 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9640. Min Act: -0.0000

Data Index: 740020 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1196127 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9597. Min Act: -0.0000

Data Index: 314514 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8752. Min Act: -0.0000

Data Index: 424173 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9554. Min Act: -0.0000

Data Index: 206744 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1640583 (Python Code)

Max Activating Token Index: 828

Text #11

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8627. Min Act: -0.0000

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9413. Min Act: -0.0000

Data Index: 484421 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9013. Min Act: -0.0000

Data Index: 865619 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1327092 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8227. Min Act: -0.0000

Data Index: 721452 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9633. Min Act: -0.0000

Data Index: 272392 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1581797 (Python Code)

Max Activating Token Index: 548

Text #18

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.9108. Min Act: -0.0000

Data Index: 970276 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 1.1289. Min Range: -1.1289

Max Act: 0.8750. Min Act: -0.0000

Data Index: 837433 (C4 (Web Text))

Max Activating Token Index: 749