Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2550 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2967. Min Range: -2.2967

Max Act: 2.2967. Min Act: -0.0000

Data Index: 1101717 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.8591. Min Act: -0.0000

Data Index: 853027 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.6872. Min Act: -0.0000

Data Index: 254076 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.5936. Min Act: -0.0000

Data Index: 646864 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.5584. Min Act: -0.0000

Data Index: 166362 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.6192. Min Act: -0.0000

Data Index: 83350 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.4367. Min Act: -0.0000

Data Index: 262913 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.5189. Min Act: -0.0000

Data Index: 202012 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1004502 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1230969 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.4069. Min Act: -0.0000

Data Index: 477600 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.3783. Min Act: -0.0000

Data Index: 305260 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.4907. Min Act: -0.0000

Data Index: 1054750 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.5869. Min Act: -0.0000

Data Index: 1075111 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.5134. Min Act: -0.0000

Data Index: 882316 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.5077. Min Act: -0.0000

Data Index: 424021 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.4218. Min Act: -0.0000

Data Index: 1129337 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.4782. Min Act: -0.0000

Data Index: 660277 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1126896 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 2.2967. Min Range: -2.2967

Max Act: 1.3159. Min Act: -0.0000

Data Index: 764046 (C4 (Web Text))

Max Activating Token Index: 756