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

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

Neuron 3675 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: 0.0391. Min Range: -0.0391

Max Act: 0.0391. Min Act: -0.0001

Data Index: 475256 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0371. Min Act: -0.0001

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1408757 (Python Code)

Max Activating Token Index: 552

Text #3

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1512714 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1432769 (Python Code)

Max Activating Token Index: 607

Text #5

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0348. Min Act: -0.0001

Data Index: 470422 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0324. Min Act: -0.0001

Data Index: 274323 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0324. Min Act: -0.0001

Data Index: 131740 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1573837 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1407664 (Python Code)

Max Activating Token Index: 879

Text #10

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1653851 (Python Code)

Max Activating Token Index: 450

Text #11

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1630634 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1542984 (Python Code)

Max Activating Token Index: 819

Text #13

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1630872 (Python Code)

Max Activating Token Index: 818

Text #14

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0314. Min Act: -0.0001

Data Index: 1457191 (Python Code)

Max Activating Token Index: 322

Text #15

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1528867 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1513431 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1419202 (Python Code)

Max Activating Token Index: 975

Text #18

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0273. Min Act: -0.0001

Data Index: 1438920 (Python Code)

Max Activating Token Index: 973

Text #19

Max Range: 0.0391. Min Range: -0.0391

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1418448 (Python Code)

Max Activating Token Index: 273