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

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

Neuron 4042 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.6185. Min Range: -10.6185

Max Act: 9.1427. Min Act: -0.0000

Data Index: 63617 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 10.6185. Min Range: -10.6185

Max Act: 10.6185. Min Act: -0.0000

Data Index: 1323268 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 10.6185. Min Range: -10.6185

Max Act: 8.3876. Min Act: -0.0000

Data Index: 536890 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 10.6185. Min Range: -10.6185

Max Act: 9.3430. Min Act: -0.0000

Data Index: 473629 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 10.6185. Min Range: -10.6185

Max Act: 8.0460. Min Act: -0.0000

Data Index: 171275 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 10.6185. Min Range: -10.6185

Max Act: 7.4482. Min Act: -0.0000

Data Index: 1158757 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 10.6185. Min Range: -10.6185

Max Act: 7.8670. Min Act: -0.0000

Data Index: 1317424 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 10.6185. Min Range: -10.6185

Max Act: 3.9984. Min Act: -0.0000

Data Index: 370729 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 10.6185. Min Range: -10.6185

Max Act: 3.6940. Min Act: -0.0000

Data Index: 1301475 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 10.6185. Min Range: -10.6185

Max Act: 4.5874. Min Act: -0.0001

Data Index: 1229178 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 10.6185. Min Range: -10.6185

Max Act: 3.9066. Min Act: -0.0001

Data Index: 1298623 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 10.6185. Min Range: -10.6185

Max Act: 3.9373. Min Act: -0.0001

Data Index: 790696 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 10.6185. Min Range: -10.6185

Max Act: 1.8104. Min Act: -0.0000

Data Index: 346626 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 10.6185. Min Range: -10.6185

Max Act: 2.9239. Min Act: -0.0001

Data Index: 815228 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 10.6185. Min Range: -10.6185

Max Act: 2.6235. Min Act: -0.0001

Data Index: 1531493 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 10.6185. Min Range: -10.6185

Max Act: 2.4181. Min Act: -0.0000

Data Index: 999544 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 10.6185. Min Range: -10.6185

Max Act: 2.2709. Min Act: -0.0000

Data Index: 428336 (C4 (Web Text))

Max Activating Token Index: 341

Text #17

Max Range: 10.6185. Min Range: -10.6185

Max Act: 1.6106. Min Act: -0.0000

Data Index: 464495 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 10.6185. Min Range: -10.6185

Max Act: 1.8327. Min Act: -0.0001

Data Index: 1487115 (Python Code)

Max Activating Token Index: 964

Text #19

Max Range: 10.6185. Min Range: -10.6185

Max Act: 1.3949. Min Act: -0.0001

Data Index: 1117888 (C4 (Web Text))

Max Activating Token Index: 33