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

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

Neuron 3562 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5566. Min Range: -3.5566

Max Act: 3.5566. Min Act: -0.0000

Data Index: 487878 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 3.5566. Min Range: -3.5566

Max Act: 3.0255. Min Act: -0.0000

Data Index: 940861 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 3.5566. Min Range: -3.5566

Max Act: 3.1316. Min Act: -0.0000

Data Index: 1326488 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.9467. Min Act: -0.0000

Data Index: 614871 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.9795. Min Act: -0.0000

Data Index: 187730 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.6463. Min Act: -0.0000

Data Index: 497738 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.6027. Min Act: -0.0000

Data Index: 992471 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.7361. Min Act: -0.0000

Data Index: 34911 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.7119. Min Act: -0.0000

Data Index: 396340 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.5634. Min Act: -0.0000

Data Index: 716815 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.6623. Min Act: -0.0000

Data Index: 1117139 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.3962. Min Act: -0.0000

Data Index: 233980 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.5090. Min Act: -0.0000

Data Index: 69238 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.3651. Min Act: -0.0000

Data Index: 415250 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.3663. Min Act: 0.0000

Data Index: 359114 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.4599. Min Act: -0.0000

Data Index: 169736 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.3357. Min Act: -0.0000

Data Index: 32458 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.5802. Min Act: -0.0000

Data Index: 546807 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.5644. Min Act: -0.0000

Data Index: 408384 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 3.5566. Min Range: -3.5566

Max Act: 2.4391. Min Act: -0.0000

Data Index: 3495 (C4 (Web Text))

Max Activating Token Index: 554