Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3502 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1888. Min Act: -0.0001

Data Index: 929442 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1636. Min Act: -0.0001

Data Index: 920551 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1212. Min Act: -0.0001

Data Index: 218916 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1207. Min Act: -0.0001

Data Index: 948820 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1191. Min Act: -0.0001

Data Index: 386584 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1212. Min Act: -0.0001

Data Index: 81772 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1177. Min Act: -0.0001

Data Index: 14659 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1093. Min Act: -0.0001

Data Index: 285141 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1184. Min Act: -0.0001

Data Index: 318883 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1241. Min Act: -0.0001

Data Index: 632974 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1080. Min Act: -0.0001

Data Index: 679721 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1119. Min Act: -0.0001

Data Index: 321727 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1098405 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1041. Min Act: -0.0001

Data Index: 603331 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1195680 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1005. Min Act: -0.0001

Data Index: 708397 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1186. Min Act: -0.0001

Data Index: 441173 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1019. Min Act: -0.0001

Data Index: 273301 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.1014. Min Act: -0.0001

Data Index: 366132 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.1888. Min Range: -0.1888

Max Act: 0.0956. Min Act: -0.0001

Data Index: 103417 (C4 (Web Text))

Max Activating Token Index: 36