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

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

Neuron 1228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1460. Min Act: -0.0001

Data Index: 497917 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1378. Min Act: -0.0001

Data Index: 809269 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1209263 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1143. Min Act: -0.0001

Data Index: 249421 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1071. Min Act: -0.0001

Data Index: 564275 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1143836 (C4 (Web Text))

Max Activating Token Index: 458

Text #6

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1062127 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1200430 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1002. Min Act: -0.0001

Data Index: 86013 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0998. Min Act: -0.0001

Data Index: 718050 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1107. Min Act: -0.0001

Data Index: 255840 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1040. Min Act: -0.0001

Data Index: 494078 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0947. Min Act: -0.0001

Data Index: 259408 (C4 (Web Text))

Max Activating Token Index: 478

Text #13

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0982. Min Act: -0.0001

Data Index: 287843 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0981. Min Act: -0.0001

Data Index: 291397 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1011. Min Act: -0.0001

Data Index: 170943 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0937. Min Act: -0.0001

Data Index: 879008 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0969. Min Act: -0.0001

Data Index: 492577 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0966. Min Act: -0.0001

Data Index: 397975 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.0959. Min Act: -0.0001

Data Index: 965302 (C4 (Web Text))

Max Activating Token Index: 883