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

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

Neuron 2771 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: 3.5724. Min Range: -3.5724

Max Act: 3.5724. Min Act: -0.0000

Data Index: 1483192 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 3.5724. Min Range: -3.5724

Max Act: 3.2154. Min Act: -0.0000

Data Index: 1455245 (Python Code)

Max Activating Token Index: 928

Text #2

Max Range: 3.5724. Min Range: -3.5724

Max Act: 3.1814. Min Act: -0.0000

Data Index: 1644796 (Python Code)

Max Activating Token Index: 410

Text #3

Max Range: 3.5724. Min Range: -3.5724

Max Act: 3.1838. Min Act: -0.0000

Data Index: 1505469 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.9843. Min Act: -0.0000

Data Index: 1375906 (Python Code)

Max Activating Token Index: 157

Text #5

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.8158. Min Act: -0.0000

Data Index: 1493518 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.9258. Min Act: -0.0000

Data Index: 1655648 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.9420. Min Act: -0.0000

Data Index: 1542453 (Python Code)

Max Activating Token Index: 832

Text #8

Max Range: 3.5724. Min Range: -3.5724

Max Act: 3.0327. Min Act: -0.0000

Data Index: 1613533 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.9142. Min Act: -0.0000

Data Index: 1583257 (Python Code)

Max Activating Token Index: 909

Text #10

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.8519. Min Act: -0.0000

Data Index: 1556599 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 3.5724. Min Range: -3.5724

Max Act: 3.0125. Min Act: -0.0000

Data Index: 1448967 (Python Code)

Max Activating Token Index: 204

Text #12

Max Range: 3.5724. Min Range: -3.5724

Max Act: 3.1695. Min Act: -0.0000

Data Index: 1501905 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.8142. Min Act: -0.0000

Data Index: 1472684 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.9573. Min Act: -0.0000

Data Index: 1618268 (Python Code)

Max Activating Token Index: 65

Text #15

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.5573. Min Act: -0.0000

Data Index: 1557660 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.9165. Min Act: -0.0000

Data Index: 1599353 (Python Code)

Max Activating Token Index: 398

Text #17

Max Range: 3.5724. Min Range: -3.5724

Max Act: 3.0697. Min Act: -0.0000

Data Index: 1396625 (Python Code)

Max Activating Token Index: 383

Text #18

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.7790. Min Act: -0.0000

Data Index: 1431367 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 3.5724. Min Range: -3.5724

Max Act: 2.7716. Min Act: -0.0000

Data Index: 1454305 (Python Code)

Max Activating Token Index: 169