Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1637 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1332123 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.3331. Min Act: -0.0000

Data Index: 187671 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1344347 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.3005. Min Act: -0.0001

Data Index: 674198 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2879. Min Act: -0.0000

Data Index: 190729 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2982. Min Act: -0.0000

Data Index: 1174107 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2737. Min Act: -0.0000

Data Index: 301395 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2798. Min Act: -0.0000

Data Index: 199229 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1134793 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2799. Min Act: -0.0000

Data Index: 974756 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2692. Min Act: -0.0000

Data Index: 13417 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2277. Min Act: -0.0000

Data Index: 884818 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1145449 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2395. Min Act: -0.0000

Data Index: 129676 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2464. Min Act: -0.0000

Data Index: 833578 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2388. Min Act: -0.0000

Data Index: 186441 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1200621 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2149. Min Act: -0.0000

Data Index: 79 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2147. Min Act: -0.0000

Data Index: 628090 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.3633. Min Range: -0.3633

Max Act: 0.2272. Min Act: -0.0000

Data Index: 773054 (C4 (Web Text))

Max Activating Token Index: 653