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

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

Neuron 4443 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5589. Min Range: -2.5589

Max Act: 2.5589. Min Act: -0.0000

Data Index: 959633 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 2.5589. Min Range: -2.5589

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1203926 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 2.5589. Min Range: -2.5589

Max Act: 2.4470. Min Act: -0.0000

Data Index: 447870 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 2.5589. Min Range: -2.5589

Max Act: 2.2668. Min Act: -0.0000

Data Index: 1266772 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.5589. Min Range: -2.5589

Max Act: 2.0473. Min Act: -0.0000

Data Index: 83595 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 2.5589. Min Range: -2.5589

Max Act: 2.1440. Min Act: -0.0000

Data Index: 286552 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 2.5589. Min Range: -2.5589

Max Act: 2.1307. Min Act: -0.0000

Data Index: 981446 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.9329. Min Act: -0.0000

Data Index: 19803 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.9270. Min Act: -0.0000

Data Index: 933021 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.8688. Min Act: -0.0000

Data Index: 1035150 (C4 (Web Text))

Max Activating Token Index: 634

Text #10

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.8584. Min Act: -0.0000

Data Index: 923989 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.9688. Min Act: -0.0000

Data Index: 58365 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.7563. Min Act: -0.0000

Data Index: 92924 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.8459. Min Act: -0.0000

Data Index: 1234022 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.7378. Min Act: -0.0000

Data Index: 419544 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.8242. Min Act: -0.0000

Data Index: 967073 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.7458. Min Act: -0.0000

Data Index: 297818 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.8147. Min Act: -0.0000

Data Index: 295950 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.8210. Min Act: -0.0000

Data Index: 1124148 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 2.5589. Min Range: -2.5589

Max Act: 1.7895. Min Act: -0.0000

Data Index: 414512 (C4 (Web Text))

Max Activating Token Index: 361