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

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

Neuron 1063 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8165. Min Act: -0.0000

Data Index: 505045 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.8505. Min Act: -0.0000

Data Index: 261091 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.7686. Min Act: -0.0000

Data Index: 470286 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5532. Min Act: -0.0000

Data Index: 138304 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1151703 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6033. Min Act: -0.0000

Data Index: 849714 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1129461 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5012. Min Act: -0.0000

Data Index: 464255 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5827. Min Act: -0.0000

Data Index: 399174 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5658. Min Act: -0.0000

Data Index: 34961 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.6104. Min Act: -0.0000

Data Index: 320850 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5462. Min Act: -0.0000

Data Index: 640288 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5390. Min Act: -0.0000

Data Index: 494426 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5539. Min Act: -0.0000

Data Index: 384386 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1005115 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.4999. Min Act: -0.0000

Data Index: 986773 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.4905. Min Act: -0.0000

Data Index: 114556 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.4893. Min Act: -0.0000

Data Index: 82607 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.4441. Min Act: -0.0000

Data Index: 101293 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 0.8505. Min Range: -0.8505

Max Act: 0.4775. Min Act: -0.0000

Data Index: 214719 (C4 (Web Text))

Max Activating Token Index: 915