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

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

Neuron 1494 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: 0.0410. Min Range: -0.0410

Max Act: 0.0410. Min Act: -0.0001

Data Index: 655816 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0385. Min Act: -0.0001

Data Index: 318601 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1624254 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0351. Min Act: -0.0001

Data Index: 660592 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0343. Min Act: -0.0001

Data Index: 334371 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0356. Min Act: -0.0001

Data Index: 283649 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1284024 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1559647 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0337. Min Act: -0.0001

Data Index: 831654 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0313. Min Act: -0.0001

Data Index: 516300 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0332. Min Act: -0.0001

Data Index: 667951 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0320. Min Act: -0.0001

Data Index: 788227 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0326. Min Act: -0.0001

Data Index: 238174 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0298. Min Act: -0.0001

Data Index: 982759 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0331. Min Act: -0.0001

Data Index: 650504 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1227578 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1555671 (Python Code)

Max Activating Token Index: 1012

Text #17

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0329. Min Act: -0.0001

Data Index: 489360 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0305. Min Act: -0.0001

Data Index: 729088 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.0410. Min Range: -0.0410

Max Act: 0.0294. Min Act: -0.0001

Data Index: 987832 (C4 (Web Text))

Max Activating Token Index: 713