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

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

Neuron 3700 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: 0.6005. Min Range: -0.6005

Max Act: 0.6005. Min Act: -0.0000

Data Index: 412618 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1046883 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.5746. Min Act: -0.0000

Data Index: 696876 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.5594. Min Act: 0.0000

Data Index: 760516 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.5260. Min Act: -0.0000

Data Index: 755485 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1288623 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.5022. Min Act: -0.0000

Data Index: 244113 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4506. Min Act: 0.0000

Data Index: 1285938 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4308. Min Act: -0.0000

Data Index: 630032 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1178739 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4429. Min Act: -0.0000

Data Index: 990615 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4310. Min Act: -0.0000

Data Index: 546466 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4386. Min Act: -0.0000

Data Index: 785174 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4002. Min Act: -0.0000

Data Index: 654231 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1008339 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4070. Min Act: -0.0000

Data Index: 565542 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.4029. Min Act: -0.0000

Data Index: 415793 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.3869. Min Act: -0.0000

Data Index: 155418 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.3751. Min Act: -0.0000

Data Index: 566547 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.6005. Min Range: -0.6005

Max Act: 0.3858. Min Act: -0.0000

Data Index: 668227 (C4 (Web Text))

Max Activating Token Index: 600