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

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

Neuron 1822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1486478 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1596. Min Act: -0.0000

Data Index: 375881 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1556. Min Act: -0.0000

Data Index: 846056 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1560. Min Act: -0.0000

Data Index: 892923 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1653855 (Python Code)

Max Activating Token Index: 383

Text #5

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1556. Min Act: -0.0000

Data Index: 246943 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1510. Min Act: -0.0000

Data Index: 258454 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1489. Min Act: -0.0000

Data Index: 675249 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1127203 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1477. Min Act: -0.0000

Data Index: 468320 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1534. Min Act: -0.0000

Data Index: 854727 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1396. Min Act: -0.0000

Data Index: 720810 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1445. Min Act: -0.0000

Data Index: 599970 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1384. Min Act: -0.0000

Data Index: 606288 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1083545 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1455. Min Act: -0.0000

Data Index: 270327 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1406. Min Act: -0.0000

Data Index: 1386071 (Python Code)

Max Activating Token Index: 281

Text #17

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1402. Min Act: -0.0000

Data Index: 165760 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1298. Min Act: -0.0000

Data Index: 1480831 (Python Code)

Max Activating Token Index: 918

Text #19

Max Range: 0.1667. Min Range: -0.1667

Max Act: 0.1382. Min Act: -0.0000

Data Index: 434292 (C4 (Web Text))

Max Activating Token Index: 24