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

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

Neuron 5029 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1823. Min Act: -0.0000

Data Index: 942433 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1492. Min Act: -0.0000

Data Index: 221850 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1535. Min Act: -0.0000

Data Index: 279745 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1571. Min Act: -0.0000

Data Index: 612646 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1550. Min Act: -0.0000

Data Index: 719343 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1496. Min Act: -0.0000

Data Index: 503277 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1493. Min Act: -0.0000

Data Index: 565765 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1479. Min Act: -0.0000

Data Index: 613503 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1500. Min Act: -0.0000

Data Index: 104502 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1400. Min Act: -0.0000

Data Index: 992915 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1036623 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1288. Min Act: -0.0000

Data Index: 805042 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1219386 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1056355 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1301. Min Act: -0.0000

Data Index: 297472 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1329. Min Act: -0.0000

Data Index: 1192532 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1282. Min Act: -0.0000

Data Index: 198047 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1324. Min Act: -0.0000

Data Index: 1202034 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1175. Min Act: -0.0000

Data Index: 212489 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.1823. Min Range: -0.1823

Max Act: 0.1253. Min Act: -0.0000

Data Index: 665398 (C4 (Web Text))

Max Activating Token Index: 304