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

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

Neuron 2209 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0361. Min Act: -0.0001

Data Index: 831817 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0359. Min Act: -0.0001

Data Index: 88062 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0341. Min Act: -0.0001

Data Index: 930179 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0340. Min Act: -0.0001

Data Index: 438424 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0323. Min Act: -0.0001

Data Index: 932279 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0311. Min Act: -0.0001

Data Index: 887512 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0295. Min Act: -0.0001

Data Index: 792503 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0302. Min Act: -0.0001

Data Index: 695573 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1048806 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1311959 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0253. Min Act: -0.0001

Data Index: 664172 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1132300 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0266. Min Act: -0.0001

Data Index: 357642 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0267. Min Act: -0.0001

Data Index: 626609 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1399928 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1102133 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0255. Min Act: -0.0001

Data Index: 537086 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0267. Min Act: -0.0001

Data Index: 532798 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0252. Min Act: -0.0001

Data Index: 965795 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0361. Min Range: -0.0361

Max Act: 0.0247. Min Act: -0.0001

Data Index: 246395 (C4 (Web Text))

Max Activating Token Index: 530