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

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

Neuron 2847 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.8727. Min Act: -0.0001

Data Index: 746168 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.4857. Min Act: -0.0001

Data Index: 529786 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.1641. Min Act: -0.0001

Data Index: 64818 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 1.8727. Min Range: -1.8727

Max Act: 1.0140. Min Act: -0.0001

Data Index: 1061622 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8969. Min Act: -0.0001

Data Index: 215189 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.9406. Min Act: -0.0001

Data Index: 1254137 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.9511. Min Act: -0.0001

Data Index: 379560 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.9996. Min Act: -0.0001

Data Index: 1013665 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.9784. Min Act: -0.0001

Data Index: 765634 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.9376. Min Act: -0.0000

Data Index: 553117 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8950. Min Act: -0.0001

Data Index: 678865 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.9975. Min Act: -0.0001

Data Index: 1052152 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.9078. Min Act: -0.0001

Data Index: 373319 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8528. Min Act: -0.0001

Data Index: 1077089 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8939. Min Act: -0.0001

Data Index: 149770 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.7518. Min Act: -0.0001

Data Index: 978279 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8598. Min Act: -0.0001

Data Index: 464215 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.7770. Min Act: -0.0001

Data Index: 173470 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.6797. Min Act: -0.0001

Data Index: 1137816 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.8727. Min Range: -1.8727

Max Act: 0.8103. Min Act: -0.0000

Data Index: 514097 (C4 (Web Text))

Max Activating Token Index: 65