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

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

Neuron 1583 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: 0.2215. Min Range: -0.2215

Max Act: 0.2215. Min Act: -0.0000

Data Index: 974409 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.2011. Min Act: -0.0000

Data Index: 936934 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1927. Min Act: -0.0000

Data Index: 325536 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1939. Min Act: -0.0000

Data Index: 211697 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1983. Min Act: -0.0000

Data Index: 600695 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1426. Min Act: -0.0000

Data Index: 772015 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1391. Min Act: -0.0000

Data Index: 1058479 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1162503 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1095001 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1044549 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1259. Min Act: -0.0000

Data Index: 946686 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1180. Min Act: -0.0000

Data Index: 107404 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1135. Min Act: -0.0000

Data Index: 241734 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1155. Min Act: -0.0000

Data Index: 184956 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1025. Min Act: -0.0000

Data Index: 517618 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1123. Min Act: -0.0000

Data Index: 526217 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1052. Min Act: -0.0000

Data Index: 117133 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1039. Min Act: -0.0000

Data Index: 837610 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1161708 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.2215. Min Range: -0.2215

Max Act: 0.1056. Min Act: -0.0000

Data Index: 734194 (C4 (Web Text))

Max Activating Token Index: 922