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

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

Neuron 5450 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1162438 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1553. Min Act: -0.0000

Data Index: 906805 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1456. Min Act: -0.0000

Data Index: 939846 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1548. Min Act: -0.0000

Data Index: 866011 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1536. Min Act: -0.0000

Data Index: 945924 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1517. Min Act: -0.0000

Data Index: 76372 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1459. Min Act: -0.0000

Data Index: 407432 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1323750 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1452. Min Act: -0.0000

Data Index: 338069 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1378. Min Act: -0.0000

Data Index: 600286 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1428. Min Act: -0.0000

Data Index: 680287 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1369. Min Act: -0.0000

Data Index: 639046 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1402. Min Act: -0.0000

Data Index: 449593 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1400. Min Act: -0.0000

Data Index: 106368 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1445. Min Act: -0.0000

Data Index: 978149 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1360. Min Act: -0.0000

Data Index: 516962 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1350. Min Act: -0.0000

Data Index: 813904 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1345. Min Act: -0.0000

Data Index: 237328 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1288. Min Act: -0.0000

Data Index: 202411 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.1881. Min Range: -0.1881

Max Act: 0.1407. Min Act: -0.0000

Data Index: 524450 (C4 (Web Text))

Max Activating Token Index: 948