Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3532 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1929. Min Act: -0.0000

Data Index: 288974 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1301981 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1617. Min Act: -0.0000

Data Index: 689151 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1549. Min Act: -0.0000

Data Index: 642975 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1485. Min Act: -0.0000

Data Index: 459071 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1372. Min Act: -0.0000

Data Index: 983796 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1413. Min Act: -0.0000

Data Index: 138099 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1508. Min Act: -0.0000

Data Index: 102844 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1454. Min Act: -0.0000

Data Index: 1037777 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1473. Min Act: -0.0000

Data Index: 196977 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1433. Min Act: -0.0000

Data Index: 934585 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1467. Min Act: -0.0000

Data Index: 934067 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1402. Min Act: -0.0000

Data Index: 567249 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1215078 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1373. Min Act: -0.0000

Data Index: 145687 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1333. Min Act: -0.0000

Data Index: 690786 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1347. Min Act: -0.0000

Data Index: 512491 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1271. Min Act: -0.0000

Data Index: 508091 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1219. Min Act: -0.0000

Data Index: 371394 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1323. Min Act: -0.0000

Data Index: 422126 (C4 (Web Text))

Max Activating Token Index: 225