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

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

Neuron 1364 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: 5.6447. Min Range: -5.6447

Max Act: 5.4194. Min Act: -0.0000

Data Index: 237016 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 5.6447. Min Range: -5.6447

Max Act: 5.4442. Min Act: -0.0000

Data Index: 1279814 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 5.6447. Min Range: -5.6447

Max Act: 5.6447. Min Act: -0.0000

Data Index: 681895 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 5.6447. Min Range: -5.6447

Max Act: 5.5017. Min Act: -0.0000

Data Index: 901819 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.7944. Min Act: -0.0000

Data Index: 924312 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.3491. Min Act: -0.0000

Data Index: 359628 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.3734. Min Act: -0.0000

Data Index: 348517 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.1697. Min Act: -0.0000

Data Index: 900679 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.0898. Min Act: -0.0000

Data Index: 581716 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.2700. Min Act: -0.0000

Data Index: 1067239 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 5.6447. Min Range: -5.6447

Max Act: 3.8963. Min Act: -0.0000

Data Index: 1282591 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.0778. Min Act: -0.0000

Data Index: 295666 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.0587. Min Act: -0.0000

Data Index: 908409 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 5.6447. Min Range: -5.6447

Max Act: 4.2024. Min Act: -0.0000

Data Index: 734108 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 5.6447. Min Range: -5.6447

Max Act: 3.7898. Min Act: -0.0000

Data Index: 1271300 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 5.6447. Min Range: -5.6447

Max Act: 3.5472. Min Act: -0.0000

Data Index: 1179286 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 5.6447. Min Range: -5.6447

Max Act: 3.4802. Min Act: -0.0000

Data Index: 950927 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 5.6447. Min Range: -5.6447

Max Act: 3.3346. Min Act: -0.0000

Data Index: 499511 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 5.6447. Min Range: -5.6447

Max Act: 3.4136. Min Act: -0.0000

Data Index: 1122467 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 5.6447. Min Range: -5.6447

Max Act: 3.1288. Min Act: -0.0000

Data Index: 430640 (C4 (Web Text))

Max Activating Token Index: 995