Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1543 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1132485 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1355464 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.4846. Min Act: -0.0000

Data Index: 742249 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.4743. Min Act: -0.0000

Data Index: 716724 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.4579. Min Act: -0.0000

Data Index: 988910 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.4559. Min Act: -0.0000

Data Index: 104951 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.4266. Min Act: -0.0000

Data Index: 548936 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.4460. Min Act: -0.0001

Data Index: 46956 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3909. Min Act: -0.0000

Data Index: 532585 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3558. Min Act: -0.0000

Data Index: 173943 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3513. Min Act: -0.0000

Data Index: 645402 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1077573 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3506. Min Act: -0.0000

Data Index: 557880 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3483. Min Act: -0.0000

Data Index: 110839 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3455. Min Act: -0.0000

Data Index: 96798 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3328. Min Act: -0.0000

Data Index: 56193 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3321. Min Act: -0.0000

Data Index: 105562 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3206. Min Act: -0.0001

Data Index: 629876 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3283. Min Act: -0.0000

Data Index: 531897 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.5457. Min Range: -0.5457

Max Act: 0.3378. Min Act: -0.0001

Data Index: 858054 (C4 (Web Text))

Max Activating Token Index: 212