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

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

Neuron 4232 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0450. Min Act: -0.0000

Data Index: 536416 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0395. Min Act: -0.0000

Data Index: 761631 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0365. Min Act: -0.0000

Data Index: 125561 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0321. Min Act: -0.0000

Data Index: 247514 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0331. Min Act: -0.0001

Data Index: 633932 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1351179 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0299. Min Act: -0.0000

Data Index: 690534 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0288. Min Act: -0.0000

Data Index: 184171 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0331. Min Act: -0.0000

Data Index: 246191 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0324. Min Act: -0.0001

Data Index: 1076522 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0333. Min Act: -0.0000

Data Index: 724856 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1222585 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1124137 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0308. Min Act: -0.0000

Data Index: 851722 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1148111 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0323. Min Act: -0.0001

Data Index: 40459 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0296. Min Act: -0.0000

Data Index: 666639 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0293. Min Act: -0.0000

Data Index: 614241 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0293. Min Act: -0.0000

Data Index: 35413 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0450. Min Range: -0.0450

Max Act: 0.0291. Min Act: -0.0000

Data Index: 274060 (C4 (Web Text))

Max Activating Token Index: 601