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

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

Neuron 4933 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0498. Min Act: -0.0003

Data Index: 46768 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0003

Data Index: 644243 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1299923 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0476. Min Act: -0.0003

Data Index: 756015 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0460. Min Act: -0.0003

Data Index: 436440 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1127343 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1057979 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0445. Min Act: -0.0003

Data Index: 740991 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0434. Min Act: -0.0003

Data Index: 399467 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0441. Min Act: -0.0002

Data Index: 666751 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0428. Min Act: -0.0003

Data Index: 627409 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0424. Min Act: -0.0003

Data Index: 370808 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0435. Min Act: -0.0003

Data Index: 128410 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0426. Min Act: -0.0003

Data Index: 117413 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0422. Min Act: -0.0003

Data Index: 78411 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0413. Min Act: -0.0002

Data Index: 472476 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0398. Min Act: -0.0003

Data Index: 941630 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1149394 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0412. Min Act: -0.0003

Data Index: 674862 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1012144 (C4 (Web Text))

Max Activating Token Index: 576