Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2832 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.9438. Min Act: -0.0000

Data Index: 261264 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.9461. Min Act: -0.0000

Data Index: 782777 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.9336. Min Act: -0.0000

Data Index: 480501 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.7340. Min Act: -0.0000

Data Index: 711521 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.8698. Min Act: -0.0000

Data Index: 455839 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.7383. Min Act: -0.0000

Data Index: 42155 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.6793. Min Act: -0.0000

Data Index: 302559 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.7190. Min Act: -0.0000

Data Index: 758543 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.6749. Min Act: -0.0000

Data Index: 1313112 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.6571. Min Act: -0.0000

Data Index: 99790 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.7199. Min Act: -0.0000

Data Index: 515364 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.6174. Min Act: -0.0000

Data Index: 1267800 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.4818. Min Act: -0.0000

Data Index: 226155 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.5666. Min Act: -0.0000

Data Index: 490465 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.6201. Min Act: -0.0000

Data Index: 173373 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.5009. Min Act: 0.0000

Data Index: 1267035 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.5083. Min Act: -0.0000

Data Index: 523166 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.4955. Min Act: -0.0000

Data Index: 1166668 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.5002. Min Act: 0.0000

Data Index: 1135292 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.9461. Min Range: -1.9461

Max Act: 1.5201. Min Act: -0.0000

Data Index: 757371 (C4 (Web Text))

Max Activating Token Index: 952