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

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

Neuron 501 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.7071. Min Act: -0.0001

Data Index: 104278 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6827. Min Act: -0.0001

Data Index: 1257724 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6343. Min Act: -0.0001

Data Index: 1246372 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5975. Min Act: -0.0001

Data Index: 666549 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5778. Min Act: -0.0001

Data Index: 683138 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5588. Min Act: -0.0001

Data Index: 426103 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5225. Min Act: -0.0001

Data Index: 950279 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5581. Min Act: -0.0001

Data Index: 445132 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5291. Min Act: -0.0001

Data Index: 470676 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5471. Min Act: -0.0001

Data Index: 268192 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5603. Min Act: -0.0001

Data Index: 675307 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5369. Min Act: -0.0001

Data Index: 83345 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4945. Min Act: -0.0001

Data Index: 332246 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5056. Min Act: -0.0001

Data Index: 581058 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5230. Min Act: -0.0001

Data Index: 505592 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4946. Min Act: -0.0001

Data Index: 744690 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5555. Min Act: -0.0001

Data Index: 1054864 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5242. Min Act: -0.0001

Data Index: 677292 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5260. Min Act: -0.0001

Data Index: 1190797 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5044. Min Act: -0.0001

Data Index: 469026 (C4 (Web Text))

Max Activating Token Index: 567