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

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

Neuron 1558 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: 2.2077. Min Range: -2.2077

Max Act: 2.2077. Min Act: -0.0000

Data Index: 230582 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.8926. Min Act: -0.0000

Data Index: 1416639 (Python Code)

Max Activating Token Index: 692

Text #2

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.7682. Min Act: -0.0000

Data Index: 1263986 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.7129. Min Act: -0.0000

Data Index: 1552647 (Python Code)

Max Activating Token Index: 520

Text #4

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.7040. Min Act: -0.0000

Data Index: 98930 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.7190. Min Act: -0.0000

Data Index: 1075724 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.7141. Min Act: -0.0000

Data Index: 673842 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.5580. Min Act: -0.0000

Data Index: 33659 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.5687. Min Act: -0.0000

Data Index: 1218877 (C4 (Web Text))

Max Activating Token Index: 185

Text #9

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.4432. Min Act: -0.0000

Data Index: 164797 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.4556. Min Act: -0.0000

Data Index: 1355407 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.5071. Min Act: -0.0000

Data Index: 777110 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.4951. Min Act: -0.0000

Data Index: 545446 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.4040. Min Act: -0.0000

Data Index: 254209 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1604627 (Python Code)

Max Activating Token Index: 565

Text #15

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.5313. Min Act: -0.0000

Data Index: 958265 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.5161. Min Act: -0.0000

Data Index: 1348290 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.4434. Min Act: -0.0000

Data Index: 50566 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.3619. Min Act: -0.0000

Data Index: 555847 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 2.2077. Min Range: -2.2077

Max Act: 1.4345. Min Act: -0.0000

Data Index: 994590 (C4 (Web Text))

Max Activating Token Index: 371