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

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

Neuron 680 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0673. Min Act: -0.0003

Data Index: 75535 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0681. Min Act: -0.0003

Data Index: 2287 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0663. Min Act: -0.0003

Data Index: 184302 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1120237 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0591. Min Act: -0.0003

Data Index: 990075 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0587. Min Act: -0.0003

Data Index: 81789 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0582. Min Act: -0.0003

Data Index: 297275 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1314092 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0568. Min Act: -0.0003

Data Index: 861255 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0554. Min Act: -0.0003

Data Index: 387607 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0504. Min Act: -0.0003

Data Index: 882015 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1109961 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1301771 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0511. Min Act: -0.0003

Data Index: 188791 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0499. Min Act: -0.0003

Data Index: 167290 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0498. Min Act: -0.0003

Data Index: 210989 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0506. Min Act: -0.0003

Data Index: 437916 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0494. Min Act: -0.0003

Data Index: 723624 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0497. Min Act: -0.0003

Data Index: 391902 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 0.0681. Min Range: -0.0681

Max Act: 0.0483. Min Act: -0.0003

Data Index: 201514 (C4 (Web Text))

Max Activating Token Index: 218