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

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

Neuron 1687 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0561. Min Act: -0.0000

Data Index: 1111721 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1418872 (Python Code)

Max Activating Token Index: 347

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0531. Min Act: -0.0000

Data Index: 466345 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1356594 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0000

Data Index: 903091 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0478. Min Act: -0.0000

Data Index: 451406 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0456. Min Act: -0.0000

Data Index: 1570916 (Python Code)

Max Activating Token Index: 427

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0457. Min Act: 0.0000

Data Index: 1370971 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0455. Min Act: -0.0000

Data Index: 699446 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0426. Min Act: -0.0000

Data Index: 1505887 (Python Code)

Max Activating Token Index: 44

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0440. Min Act: -0.0000

Data Index: 789652 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1550614 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0391. Min Act: -0.0000

Data Index: 1534823 (Python Code)

Max Activating Token Index: 316

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0398. Min Act: -0.0000

Data Index: 213634 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1535956 (Python Code)

Max Activating Token Index: 239

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0417. Min Act: -0.0000

Data Index: 981504 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1451199 (Python Code)

Max Activating Token Index: 283

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0433. Min Act: -0.0000

Data Index: 1619894 (Python Code)

Max Activating Token Index: 803

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0412. Min Act: -0.0000

Data Index: 262969 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0416. Min Act: -0.0000

Data Index: 1502770 (Python Code)

Max Activating Token Index: 100