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

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

Neuron 4747 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0460. Min Act: -0.0001

Data Index: 984929 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0605. Min Act: -0.0001

Data Index: 711792 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0504. Min Act: -0.0001

Data Index: 706530 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0508. Min Act: -0.0001

Data Index: 456351 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0378. Min Act: -0.0001

Data Index: 1208781 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0335. Min Act: -0.0001

Data Index: 468016 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0319. Min Act: -0.0001

Data Index: 691835 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0356. Min Act: -0.0001

Data Index: 583045 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0250. Min Act: -0.0001

Data Index: 570048 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0266. Min Act: -0.0001

Data Index: 474430 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0308. Min Act: -0.0001

Data Index: 1143752 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0326. Min Act: -0.0001

Data Index: 619456 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0233. Min Act: -0.0001

Data Index: 317299 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1335718 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0278. Min Act: -0.0001

Data Index: 625089 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1080580 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0267. Min Act: -0.0001

Data Index: 826414 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1154764 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0259. Min Act: -0.0001

Data Index: 168469 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0605. Min Range: -0.0605

Max Act: 0.0277. Min Act: -0.0001

Data Index: 198835 (C4 (Web Text))

Max Activating Token Index: 13