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

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

Neuron 1094 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.8024. Min Act: -0.0001

Data Index: 82984 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7903. Min Act: -0.0001

Data Index: 1274118 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7835. Min Act: -0.0001

Data Index: 1654930 (Python Code)

Max Activating Token Index: 304

Text #3

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7895. Min Act: -0.0001

Data Index: 387801 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.8087. Min Act: -0.0001

Data Index: 354833 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7315. Min Act: -0.0001

Data Index: 710211 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7772. Min Act: -0.0001

Data Index: 569843 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7555. Min Act: -0.0001

Data Index: 1516125 (Python Code)

Max Activating Token Index: 268

Text #8

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7504. Min Act: -0.0001

Data Index: 21352 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7504. Min Act: -0.0001

Data Index: 1005461 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.6994. Min Act: -0.0001

Data Index: 1524758 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7632. Min Act: -0.0001

Data Index: 735099 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7586. Min Act: -0.0001

Data Index: 886579 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.8070. Min Act: -0.0001

Data Index: 457452 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7556. Min Act: -0.0001

Data Index: 1157383 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7564. Min Act: -0.0001

Data Index: 899680 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7313. Min Act: -0.0001

Data Index: 1443863 (Python Code)

Max Activating Token Index: 800

Text #17

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7576. Min Act: -0.0001

Data Index: 638640 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7503. Min Act: -0.0001

Data Index: 1062361 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.8087. Min Range: -0.8087

Max Act: 0.7745. Min Act: -0.0001

Data Index: 922593 (C4 (Web Text))

Max Activating Token Index: 432