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

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

Neuron 1248 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7711. Min Act: -0.0002

Data Index: 1512650 (Python Code)

Max Activating Token Index: 549

Text #1

Max Range: 3.1750. Min Range: -3.1750

Max Act: 3.1750. Min Act: -0.0002

Data Index: 1625851 (Python Code)

Max Activating Token Index: 551

Text #2

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.0622. Min Act: -0.0002

Data Index: 1410027 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.5214. Min Act: -0.0002

Data Index: 1387045 (Python Code)

Max Activating Token Index: 226

Text #4

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.1427. Min Act: -0.0002

Data Index: 1639516 (Python Code)

Max Activating Token Index: 946

Text #5

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.0351. Min Act: -0.0002

Data Index: 1377758 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.2559. Min Act: -0.0002

Data Index: 1523607 (Python Code)

Max Activating Token Index: 980

Text #7

Max Range: 3.1750. Min Range: -3.1750

Max Act: 1.9836. Min Act: -0.0002

Data Index: 1623598 (Python Code)

Max Activating Token Index: 957

Text #8

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.0161. Min Act: -0.0002

Data Index: 1368446 (Python Code)

Max Activating Token Index: 514

Text #9

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.3690. Min Act: -0.0002

Data Index: 1380702 (Python Code)

Max Activating Token Index: 276

Text #10

Max Range: 3.1750. Min Range: -3.1750

Max Act: 1.8403. Min Act: -0.0002

Data Index: 1593904 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.0884. Min Act: -0.0002

Data Index: 1398340 (Python Code)

Max Activating Token Index: 66

Text #12

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.1212. Min Act: -0.0002

Data Index: 1581648 (Python Code)

Max Activating Token Index: 918

Text #13

Max Range: 3.1750. Min Range: -3.1750

Max Act: 1.9424. Min Act: -0.0002

Data Index: 1590329 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.0401. Min Act: -0.0002

Data Index: 1561725 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 3.1750. Min Range: -3.1750

Max Act: 1.9820. Min Act: -0.0002

Data Index: 1543053 (Python Code)

Max Activating Token Index: 418

Text #16

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.3004. Min Act: -0.0002

Data Index: 1455897 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 3.1750. Min Range: -3.1750

Max Act: 1.9235. Min Act: -0.0002

Data Index: 1597631 (Python Code)

Max Activating Token Index: 256

Text #18

Max Range: 3.1750. Min Range: -3.1750

Max Act: 1.9853. Min Act: -0.0002

Data Index: 1365415 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 3.1750. Min Range: -3.1750

Max Act: 1.8958. Min Act: -0.0002

Data Index: 1469707 (Python Code)

Max Activating Token Index: 149