Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1490 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0494. Min Act: -0.0002

Data Index: 387150 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0501. Min Act: -0.0002

Data Index: 629996 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0478. Min Act: -0.0002

Data Index: 882105 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0476. Min Act: -0.0002

Data Index: 454127 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1131607 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 801505 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0485. Min Act: -0.0002

Data Index: 729476 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1283876 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1107585 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0449. Min Act: -0.0002

Data Index: 309471 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0449. Min Act: -0.0001

Data Index: 43016 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1183564 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1300982 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0431. Min Act: -0.0002

Data Index: 740051 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0462. Min Act: -0.0002

Data Index: 33271 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1044271 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0424. Min Act: -0.0002

Data Index: 269804 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0406. Min Act: -0.0002

Data Index: 237352 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0446. Min Act: -0.0002

Data Index: 924424 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1153943 (C4 (Web Text))

Max Activating Token Index: 180