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

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

Neuron 2354 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: 2.1460. Min Range: -2.1460

Max Act: 2.1460. Min Act: -0.0000

Data Index: 255877 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 2.1460. Min Range: -2.1460

Max Act: 2.0022. Min Act: -0.0000

Data Index: 1133212 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.8612. Min Act: -0.0000

Data Index: 903336 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.8348. Min Act: -0.0000

Data Index: 831653 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.6838. Min Act: -0.0000

Data Index: 311039 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.6422. Min Act: -0.0000

Data Index: 352389 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.6473. Min Act: -0.0000

Data Index: 1104806 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.7252. Min Act: -0.0000

Data Index: 1067930 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5868. Min Act: -0.0000

Data Index: 564332 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5628. Min Act: -0.0000

Data Index: 271839 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5178. Min Act: -0.0000

Data Index: 871419 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.4156. Min Act: -0.0000

Data Index: 79354 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5315. Min Act: -0.0000

Data Index: 991219 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5563. Min Act: -0.0000

Data Index: 919665 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5557. Min Act: -0.0000

Data Index: 750284 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5577. Min Act: -0.0000

Data Index: 448276 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5000. Min Act: -0.0000

Data Index: 308280 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5230. Min Act: -0.0000

Data Index: 547282 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.4295. Min Act: -0.0000

Data Index: 1167034 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 2.1460. Min Range: -2.1460

Max Act: 1.5101. Min Act: -0.0000

Data Index: 824009 (C4 (Web Text))

Max Activating Token Index: 386