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

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

Neuron 727 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: 2.3287. Min Range: -2.3287

Max Act: 2.3287. Min Act: -0.0000

Data Index: 342146 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.9525. Min Act: -0.0000

Data Index: 1343284 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.9449. Min Act: -0.0000

Data Index: 738662 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 2.3287. Min Range: -2.3287

Max Act: 2.0279. Min Act: -0.0000

Data Index: 23540 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.9719. Min Act: -0.0000

Data Index: 1311931 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 2.3287. Min Range: -2.3287

Max Act: 2.1586. Min Act: -0.0000

Data Index: 436927 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.8106. Min Act: -0.0000

Data Index: 1306407 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.8783. Min Act: -0.0000

Data Index: 1272049 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.9501. Min Act: -0.0000

Data Index: 618921 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.6816. Min Act: -0.0000

Data Index: 1228843 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.7415. Min Act: -0.0001

Data Index: 942873 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.7255. Min Act: -0.0000

Data Index: 1202989 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.6191. Min Act: -0.0000

Data Index: 513058 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.4850. Min Act: -0.0000

Data Index: 72986 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.7595. Min Act: -0.0000

Data Index: 297437 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.6416. Min Act: -0.0000

Data Index: 20605 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.6395. Min Act: -0.0000

Data Index: 364216 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.5357. Min Act: -0.0000

Data Index: 766220 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.5395. Min Act: -0.0000

Data Index: 251808 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 2.3287. Min Range: -2.3287

Max Act: 1.5263. Min Act: -0.0000

Data Index: 44004 (C4 (Web Text))

Max Activating Token Index: 434