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

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

Neuron 3142 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.8029. Min Act: -0.0000

Data Index: 1378301 (Python Code)

Max Activating Token Index: 682

Text #1

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.7413. Min Act: -0.0000

Data Index: 1597503 (Python Code)

Max Activating Token Index: 946

Text #2

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.6264. Min Act: -0.0000

Data Index: 1522484 (Python Code)

Max Activating Token Index: 751

Text #3

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.5546. Min Act: -0.0000

Data Index: 1609540 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4343. Min Act: -0.0000

Data Index: 1480808 (Python Code)

Max Activating Token Index: 166

Text #5

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4642. Min Act: -0.0000

Data Index: 1481373 (Python Code)

Max Activating Token Index: 858

Text #6

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4273. Min Act: -0.0000

Data Index: 1419399 (Python Code)

Max Activating Token Index: 135

Text #7

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4339. Min Act: -0.0000

Data Index: 1496200 (Python Code)

Max Activating Token Index: 905

Text #8

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.2240. Min Act: -0.0000

Data Index: 1552141 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.1773. Min Act: -0.0000

Data Index: 1641099 (Python Code)

Max Activating Token Index: 758

Text #10

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.3428. Min Act: -0.0000

Data Index: 1564370 (Python Code)

Max Activating Token Index: 99

Text #11

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4882. Min Act: -0.0000

Data Index: 1573654 (Python Code)

Max Activating Token Index: 750

Text #12

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.1402. Min Act: -0.0000

Data Index: 1532389 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.2882. Min Act: -0.0000

Data Index: 1410417 (Python Code)

Max Activating Token Index: 343

Text #14

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4448. Min Act: -0.0000

Data Index: 1592704 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.2728. Min Act: -0.0000

Data Index: 1442136 (Python Code)

Max Activating Token Index: 988

Text #16

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4334. Min Act: -0.0000

Data Index: 1521623 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.4512. Min Act: -0.0000

Data Index: 1423245 (Python Code)

Max Activating Token Index: 730

Text #18

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.1064. Min Act: -0.0000

Data Index: 1445392 (Python Code)

Max Activating Token Index: 838

Text #19

Max Range: 4.8029. Min Range: -4.8029

Max Act: 4.0414. Min Act: -0.0000

Data Index: 1415280 (Python Code)

Max Activating Token Index: 446