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

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

Neuron 3151 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: 0.4274. Min Range: -0.4274

Max Act: 0.4274. Min Act: -0.0003

Data Index: 471059 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.4243. Min Act: -0.0003

Data Index: 13598 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.4197. Min Act: -0.0003

Data Index: 313849 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3933. Min Act: -0.0003

Data Index: 789572 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3855. Min Act: -0.0003

Data Index: 156346 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3539. Min Act: -0.0003

Data Index: 267886 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3750. Min Act: -0.0003

Data Index: 36357 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3535. Min Act: -0.0003

Data Index: 1274868 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3314. Min Act: -0.0002

Data Index: 250865 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3365. Min Act: -0.0003

Data Index: 1333357 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3373. Min Act: -0.0003

Data Index: 1312376 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3268. Min Act: -0.0003

Data Index: 32947 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3411. Min Act: -0.0003

Data Index: 567813 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3309. Min Act: -0.0003

Data Index: 617498 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3416. Min Act: -0.0002

Data Index: 1293873 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3310. Min Act: -0.0003

Data Index: 991 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3351. Min Act: -0.0003

Data Index: 1186866 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3076. Min Act: -0.0003

Data Index: 1224264 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3079. Min Act: -0.0002

Data Index: 967097 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3135. Min Act: -0.0002

Data Index: 449961 (C4 (Web Text))

Max Activating Token Index: 650