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

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

Neuron 783 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: 2.1003. Min Range: -2.1003

Max Act: 2.1003. Min Act: -0.0000

Data Index: 1197121 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.9420. Min Act: -0.0000

Data Index: 379474 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.8891. Min Act: -0.0000

Data Index: 153792 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 2.1003. Min Range: -2.1003

Max Act: 2.0568. Min Act: -0.0000

Data Index: 1120936 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.6412. Min Act: -0.0000

Data Index: 1119603 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.5369. Min Act: -0.0000

Data Index: 762595 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.4404. Min Act: -0.0000

Data Index: 844571 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.2239. Min Act: -0.0000

Data Index: 20292 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.2103. Min Act: -0.0000

Data Index: 87892 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.2177. Min Act: -0.0000

Data Index: 1175115 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.1472. Min Act: -0.0000

Data Index: 359677 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.1492. Min Act: -0.0000

Data Index: 735190 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.1778. Min Act: -0.0000

Data Index: 224329 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.1751. Min Act: -0.0000

Data Index: 715316 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.0842. Min Act: -0.0000

Data Index: 751067 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.2208. Min Act: -0.0000

Data Index: 315968 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.0858. Min Act: -0.0000

Data Index: 592504 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.1440. Min Act: -0.0000

Data Index: 194601 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.0081. Min Act: -0.0000

Data Index: 829550 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 2.1003. Min Range: -2.1003

Max Act: 1.1345. Min Act: -0.0000

Data Index: 626749 (C4 (Web Text))

Max Activating Token Index: 563