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

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

Neuron 2858 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: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1445259 (Python Code)

Max Activating Token Index: 188

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1483. Min Act: -0.0001

Data Index: 125886 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1294085 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1434. Min Act: -0.0001

Data Index: 74929 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1416. Min Act: -0.0001

Data Index: 220101 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1362. Min Act: -0.0001

Data Index: 15799 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1351. Min Act: -0.0001

Data Index: 97424 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1402. Min Act: -0.0001

Data Index: 824864 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1329. Min Act: -0.0001

Data Index: 490490 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1368. Min Act: -0.0001

Data Index: 579458 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1310. Min Act: -0.0001

Data Index: 185853 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1305. Min Act: -0.0001

Data Index: 353456 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1303. Min Act: -0.0001

Data Index: 111029 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1233. Min Act: -0.0001

Data Index: 582530 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1011424 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1250. Min Act: -0.0001

Data Index: 961472 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1204. Min Act: -0.0001

Data Index: 582321 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1294. Min Act: -0.0001

Data Index: 879124 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1153. Min Act: -0.0001

Data Index: 859454 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1284. Min Act: -0.0001

Data Index: 162673 (C4 (Web Text))

Max Activating Token Index: 543