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

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

Neuron 114 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0001

Data Index: 202718 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0429. Min Act: -0.0001

Data Index: 636048 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0398. Min Act: -0.0001

Data Index: 110319 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1307028 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0362. Min Act: -0.0001

Data Index: 622764 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0373. Min Act: -0.0001

Data Index: 250656 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0385. Min Act: -0.0001

Data Index: 1578405 (Python Code)

Max Activating Token Index: 891

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0365. Min Act: -0.0001

Data Index: 487990 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0349. Min Act: -0.0001

Data Index: 407646 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1521486 (Python Code)

Max Activating Token Index: 936

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1382167 (Python Code)

Max Activating Token Index: 583

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0310. Min Act: -0.0001

Data Index: 707955 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0323. Min Act: -0.0001

Data Index: 29455 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1473852 (Python Code)

Max Activating Token Index: 857

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0320. Min Act: -0.0001

Data Index: 763450 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1530093 (Python Code)

Max Activating Token Index: 826

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0346. Min Act: -0.0001

Data Index: 927931 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1394216 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1652339 (Python Code)

Max Activating Token Index: 889

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0321. Min Act: -0.0001

Data Index: 801750 (C4 (Web Text))

Max Activating Token Index: 885