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

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

Neuron 3696 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1565076 (Python Code)

Max Activating Token Index: 196

Text #1

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0694. Min Act: -0.0001

Data Index: 12465 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0560. Min Act: -0.0000

Data Index: 608106 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1586404 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0490. Min Act: -0.0000

Data Index: 861506 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0430. Min Act: -0.0001

Data Index: 183434 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0426. Min Act: -0.0000

Data Index: 1654467 (Python Code)

Max Activating Token Index: 696

Text #7

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0424. Min Act: -0.0000

Data Index: 365097 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0423. Min Act: -0.0001

Data Index: 802746 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0435. Min Act: -0.0000

Data Index: 230024 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0418. Min Act: -0.0000

Data Index: 171113 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0416. Min Act: -0.0000

Data Index: 755770 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1534842 (Python Code)

Max Activating Token Index: 409

Text #13

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0415. Min Act: -0.0000

Data Index: 438416 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0427. Min Act: -0.0000

Data Index: 1551694 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0441. Min Act: -0.0001

Data Index: 1194642 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0425. Min Act: -0.0000

Data Index: 310175 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1379598 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0400. Min Act: -0.0000

Data Index: 434820 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0388. Min Act: -0.0000

Data Index: 649841 (C4 (Web Text))

Max Activating Token Index: 861