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

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

Neuron 780 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.8480. Min Act: -0.0000

Data Index: 358796 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.7575. Min Act: -0.0000

Data Index: 453086 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.6599. Min Act: -0.0000

Data Index: 171368 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.4616. Min Act: -0.0000

Data Index: 793266 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.3570. Min Act: -0.0000

Data Index: 753310 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.2702. Min Act: -0.0000

Data Index: 611699 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.2554. Min Act: -0.0000

Data Index: 838525 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.2576. Min Act: -0.0000

Data Index: 314571 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.1936. Min Act: -0.0000

Data Index: 321623 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1338446 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.0801. Min Act: -0.0000

Data Index: 183665 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 1.8480. Min Range: -1.8480

Max Act: 0.9968. Min Act: -0.0000

Data Index: 619087 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 1.8480. Min Range: -1.8480

Max Act: 0.9954. Min Act: -0.0000

Data Index: 684695 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.0251. Min Act: -0.0000

Data Index: 190387 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 1.8480. Min Range: -1.8480

Max Act: 1.0338. Min Act: -0.0000

Data Index: 511961 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.8480. Min Range: -1.8480

Max Act: 0.9513. Min Act: -0.0000

Data Index: 893223 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.8480. Min Range: -1.8480

Max Act: 0.9475. Min Act: -0.0000

Data Index: 701936 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 1.8480. Min Range: -1.8480

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1228230 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.8480. Min Range: -1.8480

Max Act: 0.9272. Min Act: -0.0000

Data Index: 1586790 (Python Code)

Max Activating Token Index: 342

Text #19

Max Range: 1.8480. Min Range: -1.8480

Max Act: 0.9248. Min Act: -0.0000

Data Index: 981431 (C4 (Web Text))

Max Activating Token Index: 674