Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 830 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.3328. Min Range: -5.3328

Max Act: 5.3328. Min Act: -0.0000

Data Index: 253089 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 5.3328. Min Range: -5.3328

Max Act: 4.8010. Min Act: -0.0000

Data Index: 116085 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 5.3328. Min Range: -5.3328

Max Act: 4.0160. Min Act: -0.0000

Data Index: 1291599 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.9378. Min Act: -0.0000

Data Index: 249644 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 5.3328. Min Range: -5.3328

Max Act: 4.1338. Min Act: -0.0000

Data Index: 1054344 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 5.3328. Min Range: -5.3328

Max Act: 4.0979. Min Act: -0.0000

Data Index: 1260895 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.9302. Min Act: -0.0000

Data Index: 1219012 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.6524. Min Act: -0.0000

Data Index: 263495 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.6046. Min Act: -0.0000

Data Index: 704731 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.6201. Min Act: -0.0000

Data Index: 313301 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.6299. Min Act: -0.0001

Data Index: 485420 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.3359. Min Act: -0.0000

Data Index: 1187729 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.4478. Min Act: -0.0000

Data Index: 1318872 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.7469. Min Act: -0.0000

Data Index: 527992 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.4238. Min Act: -0.0000

Data Index: 476220 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.2688. Min Act: -0.0001

Data Index: 656441 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.5321. Min Act: -0.0000

Data Index: 351206 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.3415. Min Act: -0.0000

Data Index: 307458 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.1905. Min Act: -0.0001

Data Index: 1106190 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 5.3328. Min Range: -5.3328

Max Act: 3.3366. Min Act: -0.0000

Data Index: 464605 (C4 (Web Text))

Max Activating Token Index: 601