Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1140 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0324. Min Act: -0.0004

Data Index: 656800 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0298. Min Act: -0.0004

Data Index: 809029 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1086505 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0333. Min Act: -0.0003

Data Index: 449588 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0325. Min Act: -0.0003

Data Index: 344488 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1104435 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1274346 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0315. Min Act: -0.0003

Data Index: 873387 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0290. Min Act: -0.0003

Data Index: 306450 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0307. Min Act: -0.0004

Data Index: 523155 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1051461 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0299. Min Act: -0.0003

Data Index: 298057 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0314. Min Act: -0.0003

Data Index: 920568 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0313. Min Act: -0.0003

Data Index: 73432 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0306. Min Act: -0.0003

Data Index: 73714 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0296. Min Act: -0.0004

Data Index: 733263 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0334. Min Act: -0.0003

Data Index: 482234 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0306. Min Act: -0.0003

Data Index: 535771 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1643916 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 0.0339. Min Range: -0.0339

Max Act: 0.0293. Min Act: -0.0003

Data Index: 357426 (C4 (Web Text))

Max Activating Token Index: 887