Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1034395 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0290. Min Act: -0.0001

Data Index: 299139 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0298. Min Act: 0.0000

Data Index: 1070774 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0294. Min Act: 0.0000

Data Index: 57862 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0285. Min Act: -0.0000

Data Index: 798119 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0278. Min Act: -0.0001

Data Index: 822510 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0276. Min Act: -0.0000

Data Index: 1460852 (Python Code)

Max Activating Token Index: 849

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0278. Min Act: -0.0000

Data Index: 966157 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0272. Min Act: -0.0000

Data Index: 928870 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1219856 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1364825 (Python Code)

Max Activating Token Index: 869

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0269. Min Act: -0.0001

Data Index: 962891 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0279. Min Act: -0.0001

Data Index: 3691 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0265. Min Act: -0.0001

Data Index: 683172 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0253. Min Act: -0.0001

Data Index: 569338 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1621413 (Python Code)

Max Activating Token Index: 395

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0262. Min Act: -0.0000

Data Index: 1387134 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0263. Min Act: -0.0000

Data Index: 1013470 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0269. Min Act: -0.0000

Data Index: 413136 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0253. Min Act: -0.0001

Data Index: 535590 (C4 (Web Text))

Max Activating Token Index: 243