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

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

Neuron 2428 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1560. Min Act: -0.0001

Data Index: 17548 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1012595 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1509. Min Act: -0.0001

Data Index: 458406 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1344. Min Act: -0.0001

Data Index: 1122690 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1353. Min Act: -0.0001

Data Index: 444485 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1245. Min Act: -0.0001

Data Index: 713513 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1025340 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1226. Min Act: -0.0001

Data Index: 162990 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1348. Min Act: -0.0001

Data Index: 116490 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1189626 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1315748 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1239. Min Act: -0.0001

Data Index: 448551 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1174. Min Act: -0.0001

Data Index: 419860 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1272. Min Act: -0.0001

Data Index: 747877 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1075833 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1306. Min Act: -0.0001

Data Index: 977544 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1345. Min Act: -0.0001

Data Index: 165188 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1362. Min Act: -0.0001

Data Index: 477667 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1248. Min Act: -0.0001

Data Index: 908069 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.1560. Min Range: -0.1560

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1118286 (C4 (Web Text))

Max Activating Token Index: 133