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

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

Neuron 1254 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: 1.5163. Min Range: -1.5163

Max Act: 1.5163. Min Act: -0.0000

Data Index: 1437132 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.2670. Min Act: -0.0000

Data Index: 729816 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1273441 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1468587 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.1155. Min Act: -0.0000

Data Index: 229982 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1530218 (Python Code)

Max Activating Token Index: 298

Text #6

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.0021. Min Act: -0.0000

Data Index: 233339 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9619. Min Act: -0.0000

Data Index: 387026 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1451040 (Python Code)

Max Activating Token Index: 501

Text #9

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9780. Min Act: -0.0000

Data Index: 592795 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1585280 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 1.5163. Min Range: -1.5163

Max Act: 1.0324. Min Act: -0.0000

Data Index: 208194 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9998. Min Act: -0.0000

Data Index: 511328 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9242. Min Act: -0.0000

Data Index: 192010 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9806. Min Act: -0.0000

Data Index: 1371104 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.8826. Min Act: -0.0000

Data Index: 940319 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1449364 (Python Code)

Max Activating Token Index: 812

Text #17

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9329. Min Act: -0.0000

Data Index: 1374849 (Python Code)

Max Activating Token Index: 316

Text #18

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1371751 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 1.5163. Min Range: -1.5163

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1649038 (Python Code)

Max Activating Token Index: 1019