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

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

Neuron 4481 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.6164. Min Act: 0.0000

Data Index: 225562 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1079858 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4356. Min Act: -0.0000

Data Index: 98754 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4767. Min Act: -0.0000

Data Index: 74376 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4564. Min Act: -0.0000

Data Index: 747815 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4786. Min Act: -0.0000

Data Index: 625726 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4175. Min Act: -0.0000

Data Index: 609714 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4151. Min Act: -0.0000

Data Index: 968891 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4065. Min Act: -0.0000

Data Index: 429352 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1218735 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4134. Min Act: -0.0000

Data Index: 946729 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4260. Min Act: -0.0000

Data Index: 388610 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.4066. Min Act: -0.0000

Data Index: 297001 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1232360 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.3496. Min Act: -0.0000

Data Index: 56609 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.3698. Min Act: -0.0000

Data Index: 170597 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.3752. Min Act: -0.0000

Data Index: 252501 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.3719. Min Act: -0.0000

Data Index: 453339 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.3176. Min Act: -0.0000

Data Index: 1032592 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.6306. Min Range: -0.6306

Max Act: 0.3458. Min Act: -0.0000

Data Index: 997739 (C4 (Web Text))

Max Activating Token Index: 243