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

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

Neuron 905 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4793. Min Act: 0.0000

Data Index: 321803 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4330. Min Act: -0.0000

Data Index: 654592 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4618. Min Act: 0.0000

Data Index: 6287 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4212. Min Act: -0.0000

Data Index: 897359 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.4011. Min Act: -0.0000

Data Index: 538120 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3971. Min Act: -0.0000

Data Index: 574087 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3823. Min Act: -0.0000

Data Index: 645608 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3757. Min Act: 0.0000

Data Index: 62431 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3674. Min Act: 0.0000

Data Index: 1036784 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3659. Min Act: -0.0000

Data Index: 462516 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3488. Min Act: 0.0000

Data Index: 831194 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3571. Min Act: -0.0000

Data Index: 177620 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1289713 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3329. Min Act: -0.0000

Data Index: 274939 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3303. Min Act: 0.0000

Data Index: 371677 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1151295 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3408. Min Act: -0.0000

Data Index: 833878 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3283. Min Act: -0.0000

Data Index: 911058 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3079. Min Act: -0.0000

Data Index: 877340 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.4793. Min Range: -0.4793

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1089326 (C4 (Web Text))

Max Activating Token Index: 853