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

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

Neuron 2450 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: 2.3409. Min Range: -2.3409

Max Act: 2.3409. Min Act: -0.0000

Data Index: 1609901 (Python Code)

Max Activating Token Index: 674

Text #1

Max Range: 2.3409. Min Range: -2.3409

Max Act: 2.3245. Min Act: -0.0000

Data Index: 1374722 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 2.3409. Min Range: -2.3409

Max Act: 2.2994. Min Act: -0.0000

Data Index: 342673 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 2.3409. Min Range: -2.3409

Max Act: 2.2016. Min Act: -0.0000

Data Index: 1440056 (Python Code)

Max Activating Token Index: 230

Text #4

Max Range: 2.3409. Min Range: -2.3409

Max Act: 2.1779. Min Act: -0.0000

Data Index: 1506123 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 2.3409. Min Range: -2.3409

Max Act: 2.1537. Min Act: -0.0000

Data Index: 189021 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 2.3409. Min Range: -2.3409

Max Act: 2.1851. Min Act: -0.0000

Data Index: 335487 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.8623. Min Act: -0.0000

Data Index: 1166207 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.9415. Min Act: -0.0000

Data Index: 1492676 (Python Code)

Max Activating Token Index: 969

Text #9

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.9082. Min Act: -0.0000

Data Index: 619537 (C4 (Web Text))

Max Activating Token Index: 129

Text #10

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.9149. Min Act: -0.0000

Data Index: 656092 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.8847. Min Act: -0.0000

Data Index: 1501930 (Python Code)

Max Activating Token Index: 172

Text #12

Max Range: 2.3409. Min Range: -2.3409

Max Act: 2.0788. Min Act: -0.0000

Data Index: 526719 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.8613. Min Act: -0.0000

Data Index: 1473787 (Python Code)

Max Activating Token Index: 505

Text #14

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.8194. Min Act: -0.0000

Data Index: 285289 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.9236. Min Act: -0.0000

Data Index: 137715 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.6786. Min Act: -0.0000

Data Index: 1495245 (Python Code)

Max Activating Token Index: 67

Text #17

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.6445. Min Act: -0.0000

Data Index: 137321 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.7357. Min Act: -0.0000

Data Index: 1576892 (Python Code)

Max Activating Token Index: 617

Text #19

Max Range: 2.3409. Min Range: -2.3409

Max Act: 1.6449. Min Act: -0.0000

Data Index: 778886 (C4 (Web Text))

Max Activating Token Index: 789