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

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

Neuron 1989 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0253. Min Range: -2.0253

Max Act: 2.0253. Min Act: -0.0000

Data Index: 173504 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.9562. Min Act: -0.0000

Data Index: 1290739 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.9523. Min Act: -0.0000

Data Index: 52151 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.8362. Min Act: -0.0000

Data Index: 613660 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.7576. Min Act: -0.0000

Data Index: 863630 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.8594. Min Act: -0.0000

Data Index: 1070390 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.7578. Min Act: -0.0000

Data Index: 196520 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.6552. Min Act: -0.0000

Data Index: 688163 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.7366. Min Act: -0.0000

Data Index: 298124 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.8325. Min Act: -0.0000

Data Index: 482954 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.6455. Min Act: -0.0000

Data Index: 1335369 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.6410. Min Act: -0.0000

Data Index: 1163799 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.3966. Min Act: -0.0000

Data Index: 853313 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.6601. Min Act: -0.0000

Data Index: 666410 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5586. Min Act: -0.0000

Data Index: 669330 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.4651. Min Act: -0.0000

Data Index: 510360 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5119. Min Act: -0.0000

Data Index: 714209 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.4089. Min Act: -0.0000

Data Index: 33302 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.5559. Min Act: -0.0000

Data Index: 814877 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 2.0253. Min Range: -2.0253

Max Act: 1.4730. Min Act: -0.0000

Data Index: 330388 (C4 (Web Text))

Max Activating Token Index: 92