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

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

Neuron 3770 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: 7.3883. Min Range: -7.3883

Max Act: 7.3883. Min Act: -0.0000

Data Index: 215817 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.2022. Min Act: -0.0000

Data Index: 478288 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 7.3883. Min Range: -7.3883

Max Act: 6.0071. Min Act: -0.0000

Data Index: 934117 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.6783. Min Act: -0.0000

Data Index: 1271393 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.6987. Min Act: -0.0000

Data Index: 1086017 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.5116. Min Act: -0.0000

Data Index: 1261248 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.5839. Min Act: -0.0000

Data Index: 594767 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.3388. Min Act: -0.0000

Data Index: 728699 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.1710. Min Act: -0.0000

Data Index: 686227 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.4188. Min Act: -0.0000

Data Index: 1059234 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.2342. Min Act: -0.0000

Data Index: 1113330 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.4115. Min Act: -0.0000

Data Index: 868192 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.4007. Min Act: -0.0000

Data Index: 777524 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.0069. Min Act: -0.0000

Data Index: 1031657 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.2017. Min Act: -0.0000

Data Index: 23400 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.0069. Min Act: -0.0000

Data Index: 301925 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.3497. Min Act: -0.0000

Data Index: 1011365 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.4886. Min Act: -0.0000

Data Index: 476957 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.0115. Min Act: -0.0000

Data Index: 191403 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 7.3883. Min Range: -7.3883

Max Act: 5.2024. Min Act: -0.0000

Data Index: 865257 (C4 (Web Text))

Max Activating Token Index: 14