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

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

Neuron 3262 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1222653 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6525. Min Act: -0.0000

Data Index: 367297 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6272. Min Act: -0.0000

Data Index: 635523 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6069. Min Act: -0.0000

Data Index: 670596 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6204. Min Act: -0.0000

Data Index: 710435 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5937. Min Act: -0.0000

Data Index: 114379 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5905. Min Act: -0.0000

Data Index: 929921 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1173688 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.6112. Min Act: -0.0000

Data Index: 367036 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5506. Min Act: -0.0000

Data Index: 560716 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5783. Min Act: -0.0000

Data Index: 13567 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5439. Min Act: -0.0000

Data Index: 313602 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1293697 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5421. Min Act: -0.0000

Data Index: 10852 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5622. Min Act: -0.0000

Data Index: 105723 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5802. Min Act: -0.0000

Data Index: 693558 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5414. Min Act: -0.0000

Data Index: 503237 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5373. Min Act: -0.0000

Data Index: 372451 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5396. Min Act: -0.0000

Data Index: 129372 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.6589. Min Range: -0.6589

Max Act: 0.5345. Min Act: -0.0000

Data Index: 26685 (C4 (Web Text))

Max Activating Token Index: 141