Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 779 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1721. Min Act: -0.0002

Data Index: 1278258 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1551. Min Act: -0.0002

Data Index: 884951 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1507. Min Act: -0.0002

Data Index: 765527 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1481. Min Act: -0.0002

Data Index: 299293 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1475. Min Act: -0.0002

Data Index: 367553 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1418. Min Act: -0.0002

Data Index: 864945 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1423. Min Act: -0.0002

Data Index: 1338927 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1433. Min Act: -0.0002

Data Index: 45542 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1428. Min Act: -0.0002

Data Index: 616346 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1371. Min Act: -0.0002

Data Index: 483401 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1401. Min Act: -0.0002

Data Index: 1282162 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1295117 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1399. Min Act: -0.0002

Data Index: 611092 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1369. Min Act: -0.0002

Data Index: 833921 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1363. Min Act: -0.0002

Data Index: 1337181 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1350. Min Act: -0.0002

Data Index: 1290278 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1347. Min Act: -0.0003

Data Index: 406836 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1336. Min Act: -0.0002

Data Index: 448637 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1008473 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.1721. Min Range: -0.1721

Max Act: 0.1364. Min Act: -0.0002

Data Index: 562956 (C4 (Web Text))

Max Activating Token Index: 562