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

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

Neuron 2965 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5498. Min Range: -5.5498

Max Act: 5.5498. Min Act: -0.0000

Data Index: 26905 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 5.5498. Min Range: -5.5498

Max Act: 5.3161. Min Act: -0.0000

Data Index: 880898 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 5.5498. Min Range: -5.5498

Max Act: 4.7089. Min Act: -0.0000

Data Index: 150179 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 5.5498. Min Range: -5.5498

Max Act: 4.6802. Min Act: -0.0000

Data Index: 296403 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 5.5498. Min Range: -5.5498

Max Act: 4.3513. Min Act: -0.0000

Data Index: 333921 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 5.5498. Min Range: -5.5498

Max Act: 4.1879. Min Act: -0.0000

Data Index: 1135192 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.9784. Min Act: -0.0000

Data Index: 691656 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.9483. Min Act: -0.0000

Data Index: 941716 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.9123. Min Act: -0.0000

Data Index: 1546284 (Python Code)

Max Activating Token Index: 940

Text #9

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.8603. Min Act: -0.0000

Data Index: 40728 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 5.5498. Min Range: -5.5498

Max Act: 4.2111. Min Act: -0.0000

Data Index: 321691 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 5.5498. Min Range: -5.5498

Max Act: 4.1844. Min Act: -0.0000

Data Index: 292684 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.8024. Min Act: -0.0000

Data Index: 929435 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.7338. Min Act: -0.0000

Data Index: 1235829 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.6364. Min Act: -0.0000

Data Index: 724909 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.9360. Min Act: -0.0000

Data Index: 257068 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.7557. Min Act: -0.0000

Data Index: 1081917 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.7632. Min Act: -0.0000

Data Index: 1323520 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.8886. Min Act: -0.0000

Data Index: 993434 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 5.5498. Min Range: -5.5498

Max Act: 3.4373. Min Act: -0.0000

Data Index: 543822 (C4 (Web Text))

Max Activating Token Index: 773