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

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

Neuron 4198 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0000

Data Index: 151736 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1387815 (Python Code)

Max Activating Token Index: 170

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1599409 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1229. Min Act: -0.0000

Data Index: 1643564 (Python Code)

Max Activating Token Index: 810

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1141. Min Act: -0.0000

Data Index: 321925 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1004058 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1399494 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1638361 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1576710 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1252785 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1562161 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1003. Min Act: -0.0000

Data Index: 772458 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1046. Min Act: -0.0000

Data Index: 604074 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1273402 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1378767 (Python Code)

Max Activating Token Index: 1001

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1395787 (Python Code)

Max Activating Token Index: 920

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1334830 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0886. Min Act: -0.0000

Data Index: 735149 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.0977. Min Act: -0.0000

Data Index: 785386 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1074. Min Act: -0.0000

Data Index: 853630 (C4 (Web Text))

Max Activating Token Index: 502