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

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

Neuron 268 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: 3.2482. Min Range: -3.2482

Max Act: 3.2482. Min Act: -0.0000

Data Index: 115712 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.7297. Min Act: -0.0000

Data Index: 1098961 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.6945. Min Act: -0.0000

Data Index: 128346 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.3254. Min Act: -0.0000

Data Index: 1281862 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.2078. Min Act: -0.0000

Data Index: 24290 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.4217. Min Act: -0.0000

Data Index: 298402 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.1485. Min Act: -0.0000

Data Index: 388144 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.3635. Min Act: -0.0000

Data Index: 783514 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.1012. Min Act: -0.0000

Data Index: 943403 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.3319. Min Act: -0.0000

Data Index: 1245236 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.1665. Min Act: -0.0000

Data Index: 77006 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 3.2482. Min Range: -3.2482

Max Act: 1.9483. Min Act: -0.0000

Data Index: 1175545 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.3847. Min Act: -0.0000

Data Index: 962641 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 3.2482. Min Range: -3.2482

Max Act: 1.9443. Min Act: -0.0000

Data Index: 557826 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 3.2482. Min Range: -3.2482

Max Act: 1.9578. Min Act: -0.0000

Data Index: 842369 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 3.2482. Min Range: -3.2482

Max Act: 1.9570. Min Act: -0.0000

Data Index: 740282 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.0411. Min Act: -0.0000

Data Index: 829444 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 3.2482. Min Range: -3.2482

Max Act: 1.9473. Min Act: -0.0000

Data Index: 1297166 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.1347. Min Act: -0.0001

Data Index: 1138720 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 3.2482. Min Range: -3.2482

Max Act: 2.0099. Min Act: -0.0000

Data Index: 1317242 (C4 (Web Text))

Max Activating Token Index: 375