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

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

Neuron 4915 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: 2.5483. Min Range: -2.5483

Max Act: 2.3932. Min Act: 0.0001

Data Index: 1621946 (Python Code)

Max Activating Token Index: 73

Text #1

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.5425. Min Act: -0.0000

Data Index: 1403912 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.5483. Min Act: 0.0000

Data Index: 1465321 (Python Code)

Max Activating Token Index: 464

Text #3

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.1393. Min Act: -0.0000

Data Index: 1590622 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.3712. Min Act: -0.0000

Data Index: 1599247 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.2142. Min Act: 0.0001

Data Index: 1645721 (Python Code)

Max Activating Token Index: 816

Text #6

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.1602. Min Act: -0.0000

Data Index: 1503549 (Python Code)

Max Activating Token Index: 338

Text #7

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.2266. Min Act: -0.0000

Data Index: 1564600 (Python Code)

Max Activating Token Index: 436

Text #8

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.1122. Min Act: -0.0000

Data Index: 1406270 (Python Code)

Max Activating Token Index: 480

Text #9

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.3272. Min Act: -0.0000

Data Index: 1487097 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.1058. Min Act: -0.0000

Data Index: 1624715 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.1846. Min Act: -0.0000

Data Index: 1648943 (Python Code)

Max Activating Token Index: 808

Text #12

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.0462. Min Act: 0.0001

Data Index: 1411300 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.0038. Min Act: -0.0000

Data Index: 1591185 (Python Code)

Max Activating Token Index: 344

Text #14

Max Range: 2.5483. Min Range: -2.5483

Max Act: 1.9983. Min Act: -0.0000

Data Index: 1398296 (Python Code)

Max Activating Token Index: 788

Text #15

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.0704. Min Act: -0.0000

Data Index: 1429381 (Python Code)

Max Activating Token Index: 62

Text #16

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.0756. Min Act: -0.0000

Data Index: 1489106 (Python Code)

Max Activating Token Index: 714

Text #17

Max Range: 2.5483. Min Range: -2.5483

Max Act: 1.9263. Min Act: -0.0000

Data Index: 1376690 (Python Code)

Max Activating Token Index: 601

Text #18

Max Range: 2.5483. Min Range: -2.5483

Max Act: 2.0161. Min Act: -0.0000

Data Index: 1442610 (Python Code)

Max Activating Token Index: 1011

Text #19

Max Range: 2.5483. Min Range: -2.5483

Max Act: 1.9001. Min Act: -0.0000

Data Index: 1519583 (Python Code)

Max Activating Token Index: 878