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

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

Neuron 3068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1606. Min Act: -0.0003

Data Index: 224212 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1350. Min Act: -0.0003

Data Index: 399932 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1367. Min Act: -0.0003

Data Index: 1085604 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1421. Min Act: -0.0003

Data Index: 910480 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1360. Min Act: -0.0003

Data Index: 1165229 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1431. Min Act: -0.0003

Data Index: 880557 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1424. Min Act: -0.0003

Data Index: 417586 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1265. Min Act: -0.0003

Data Index: 285856 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1302. Min Act: -0.0003

Data Index: 162579 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1299. Min Act: -0.0003

Data Index: 1305657 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1286. Min Act: -0.0003

Data Index: 1412866 (Python Code)

Max Activating Token Index: 897

Text #11

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1270. Min Act: -0.0003

Data Index: 1149844 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1409. Min Act: -0.0003

Data Index: 673055 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1266. Min Act: -0.0003

Data Index: 918506 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1312. Min Act: -0.0003

Data Index: 1224216 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1211. Min Act: -0.0003

Data Index: 933929 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1233. Min Act: -0.0003

Data Index: 1566134 (Python Code)

Max Activating Token Index: 950

Text #17

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1277. Min Act: -0.0003

Data Index: 475283 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1288. Min Act: -0.0003

Data Index: 432714 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1329. Min Act: -0.0003

Data Index: 292568 (C4 (Web Text))

Max Activating Token Index: 531