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

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

Neuron 4048 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: 0.5338. Min Range: -0.5338

Max Act: 0.5338. Min Act: -0.0001

Data Index: 895070 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.5159. Min Act: -0.0001

Data Index: 725291 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4338. Min Act: -0.0001

Data Index: 684445 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4187. Min Act: -0.0001

Data Index: 434185 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4118. Min Act: -0.0001

Data Index: 90077 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3930. Min Act: -0.0001

Data Index: 236200 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4004. Min Act: -0.0001

Data Index: 1290690 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3985. Min Act: -0.0001

Data Index: 1300740 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.4131. Min Act: -0.0001

Data Index: 680824 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3781. Min Act: -0.0001

Data Index: 1167217 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3756. Min Act: -0.0001

Data Index: 170901 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3733. Min Act: -0.0001

Data Index: 478562 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3933. Min Act: -0.0001

Data Index: 456929 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3803. Min Act: -0.0001

Data Index: 232836 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3760. Min Act: -0.0001

Data Index: 1282208 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3769. Min Act: -0.0001

Data Index: 259245 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3851. Min Act: -0.0001

Data Index: 713162 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3732. Min Act: -0.0001

Data Index: 527043 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3932. Min Act: -0.0001

Data Index: 327343 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.5338. Min Range: -0.5338

Max Act: 0.3614. Min Act: -0.0001

Data Index: 206873 (C4 (Web Text))

Max Activating Token Index: 535