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

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

Neuron 4817 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8773. Min Act: -0.0000

Data Index: 443128 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1160511 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1232015 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7357. Min Act: -0.0000

Data Index: 1293482 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1082327 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6976. Min Act: -0.0000

Data Index: 534763 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7192. Min Act: -0.0000

Data Index: 192730 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7201. Min Act: -0.0000

Data Index: 599062 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1225379 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7412. Min Act: -0.0000

Data Index: 329848 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1209608 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6121. Min Act: -0.0000

Data Index: 703358 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6366. Min Act: -0.0000

Data Index: 243209 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1030292 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6208. Min Act: -0.0000

Data Index: 382566 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6361. Min Act: -0.0000

Data Index: 779320 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6019. Min Act: -0.0000

Data Index: 597062 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6017. Min Act: -0.0000

Data Index: 600305 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5772. Min Act: -0.0000

Data Index: 649284 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5915. Min Act: -0.0000

Data Index: 139531 (C4 (Web Text))

Max Activating Token Index: 690