Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 208 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0001

Data Index: 190143 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1629784 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0354. Min Act: -0.0001

Data Index: 813064 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0380. Min Act: -0.0001

Data Index: 619937 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1422627 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1071593 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1560095 (Python Code)

Max Activating Token Index: 446

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0331. Min Act: -0.0001

Data Index: 259566 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0312. Min Act: -0.0001

Data Index: 633307 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0304. Min Act: -0.0001

Data Index: 205226 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1531572 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1257134 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0293. Min Act: -0.0001

Data Index: 686660 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1630002 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0294. Min Act: -0.0001

Data Index: 525926 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0316. Min Act: -0.0001

Data Index: 1420165 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0265. Min Act: -0.0001

Data Index: 504075 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1105852 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0279. Min Act: -0.0001

Data Index: 115235 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0244. Min Act: -0.0001

Data Index: 101204 (C4 (Web Text))

Max Activating Token Index: 760