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

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

Neuron 595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.2730. Min Act: -0.0000

Data Index: 361055 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.3133. Min Act: -0.0000

Data Index: 722623 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.2285. Min Act: -0.0000

Data Index: 1089130 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.0804. Min Act: -0.0000

Data Index: 828178 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.0628. Min Act: -0.0000

Data Index: 269814 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.0246. Min Act: -0.0001

Data Index: 809645 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.0809. Min Act: -0.0000

Data Index: 107482 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 2.5670. Min Range: -2.5670

Max Act: 1.8438. Min Act: -0.0000

Data Index: 952630 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.0162. Min Act: -0.0000

Data Index: 732967 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.0082. Min Act: -0.0000

Data Index: 58937 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.0919. Min Act: -0.0000

Data Index: 446106 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.5670. Min Act: -0.0000

Data Index: 14996 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 2.5670. Min Range: -2.5670

Max Act: 1.7499. Min Act: -0.0000

Data Index: 374024 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 2.5670. Min Range: -2.5670

Max Act: 1.8837. Min Act: -0.0000

Data Index: 1216612 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 2.5670. Min Range: -2.5670

Max Act: 2.2246. Min Act: -0.0000

Data Index: 663124 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 2.5670. Min Range: -2.5670

Max Act: 1.9723. Min Act: -0.0000

Data Index: 897826 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 2.5670. Min Range: -2.5670

Max Act: 1.8443. Min Act: -0.0001

Data Index: 1026928 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 2.5670. Min Range: -2.5670

Max Act: 1.8285. Min Act: -0.0000

Data Index: 1151516 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 2.5670. Min Range: -2.5670

Max Act: 1.9766. Min Act: -0.0001

Data Index: 88623 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 2.5670. Min Range: -2.5670

Max Act: 1.8266. Min Act: -0.0000

Data Index: 1200627 (C4 (Web Text))

Max Activating Token Index: 506