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

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

Neuron 3821 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.6041. Min Act: -0.0001

Data Index: 1629550 (Python Code)

Max Activating Token Index: 265

Text #1

Max Range: 3.6041. Min Range: -3.6041

Max Act: 3.1487. Min Act: -0.0001

Data Index: 1482718 (Python Code)

Max Activating Token Index: 767

Text #2

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.9467. Min Act: -0.0001

Data Index: 1562564 (Python Code)

Max Activating Token Index: 949

Text #3

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.9355. Min Act: -0.0001

Data Index: 1510997 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.8929. Min Act: -0.0001

Data Index: 1433637 (Python Code)

Max Activating Token Index: 612

Text #5

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.5887. Min Act: -0.0001

Data Index: 1531027 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.6931. Min Act: -0.0001

Data Index: 1460747 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.4531. Min Act: -0.0001

Data Index: 1369392 (Python Code)

Max Activating Token Index: 1009

Text #8

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.4413. Min Act: -0.0001

Data Index: 1441953 (Python Code)

Max Activating Token Index: 932

Text #9

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.5182. Min Act: -0.0001

Data Index: 1617411 (Python Code)

Max Activating Token Index: 925

Text #10

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.6261. Min Act: -0.0001

Data Index: 1655761 (Python Code)

Max Activating Token Index: 98

Text #11

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.3317. Min Act: -0.0001

Data Index: 1429770 (Python Code)

Max Activating Token Index: 25

Text #12

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.6798. Min Act: -0.0001

Data Index: 1383232 (Python Code)

Max Activating Token Index: 856

Text #13

Max Range: 3.6041. Min Range: -3.6041

Max Act: 1.8603. Min Act: -0.0001

Data Index: 1645727 (Python Code)

Max Activating Token Index: 844

Text #14

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.5395. Min Act: -0.0001

Data Index: 1578239 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.4196. Min Act: -0.0001

Data Index: 1416865 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.5201. Min Act: -0.0001

Data Index: 1401671 (Python Code)

Max Activating Token Index: 593

Text #17

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.1569. Min Act: -0.0001

Data Index: 1485036 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.2536. Min Act: -0.0001

Data Index: 1465658 (Python Code)

Max Activating Token Index: 503

Text #19

Max Range: 3.6041. Min Range: -3.6041

Max Act: 2.3705. Min Act: -0.0001

Data Index: 1595155 (Python Code)

Max Activating Token Index: 154