Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3001 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0988. Min Act: -0.0002

Data Index: 25315 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0878. Min Act: -0.0002

Data Index: 899180 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0758. Min Act: -0.0002

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1173766 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1234186 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0669. Min Act: -0.0002

Data Index: 419037 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1026948 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1128733 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0672. Min Act: -0.0002

Data Index: 168568 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1166894 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1019712 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1042351 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0563. Min Act: -0.0002

Data Index: 869391 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0565. Min Act: -0.0002

Data Index: 91486 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1424097 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0564. Min Act: -0.0002

Data Index: 141299 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0519. Min Act: -0.0002

Data Index: 419846 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0550. Min Act: -0.0002

Data Index: 779686 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0593. Min Act: -0.0002

Data Index: 365896 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.0988. Min Range: -0.0988

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1648161 (Python Code)

Max Activating Token Index: 376