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

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

Neuron 4512 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9594. Min Range: -3.9594

Max Act: 3.9594. Min Act: -0.0000

Data Index: 1433588 (Python Code)

Max Activating Token Index: 1021

Text #1

Max Range: 3.9594. Min Range: -3.9594

Max Act: 3.8626. Min Act: -0.0000

Data Index: 1387724 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 3.9594. Min Range: -3.9594

Max Act: 3.2099. Min Act: -0.0000

Data Index: 1408162 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 3.9594. Min Range: -3.9594

Max Act: 3.1038. Min Act: -0.0000

Data Index: 1498437 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.7313. Min Act: -0.0000

Data Index: 1408667 (Python Code)

Max Activating Token Index: 861

Text #5

Max Range: 3.9594. Min Range: -3.9594

Max Act: 3.1173. Min Act: -0.0000

Data Index: 1554545 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.9694. Min Act: -0.0000

Data Index: 1431737 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.8195. Min Act: -0.0000

Data Index: 1544230 (Python Code)

Max Activating Token Index: 876

Text #8

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.9240. Min Act: -0.0000

Data Index: 1614598 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.9236. Min Act: -0.0000

Data Index: 1625737 (Python Code)

Max Activating Token Index: 966

Text #10

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.8854. Min Act: -0.0000

Data Index: 1496135 (Python Code)

Max Activating Token Index: 502

Text #11

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.8418. Min Act: -0.0000

Data Index: 1545339 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.5623. Min Act: -0.0000

Data Index: 1570953 (Python Code)

Max Activating Token Index: 883

Text #13

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.8189. Min Act: -0.0000

Data Index: 1590875 (Python Code)

Max Activating Token Index: 651

Text #14

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.8307. Min Act: -0.0000

Data Index: 1537834 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.8205. Min Act: -0.0000

Data Index: 1390787 (Python Code)

Max Activating Token Index: 425

Text #16

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.8162. Min Act: -0.0000

Data Index: 1429886 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.6828. Min Act: -0.0000

Data Index: 1489301 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.7992. Min Act: -0.0000

Data Index: 1558373 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 3.9594. Min Range: -3.9594

Max Act: 2.8123. Min Act: -0.0000

Data Index: 1496022 (Python Code)

Max Activating Token Index: 670