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

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

Neuron 2685 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.8534. Min Act: -0.0000

Data Index: 116617 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1434898 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.3142. Min Act: -0.0000

Data Index: 1378514 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.0657. Min Act: -0.0000

Data Index: 1402285 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1397848 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1489652 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1412509 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1369326 (Python Code)

Max Activating Token Index: 488

Text #8

Max Range: 1.8534. Min Range: -1.8534

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1093871 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.9532. Min Act: -0.0000

Data Index: 625526 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.9196. Min Act: -0.0000

Data Index: 1638312 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1446970 (Python Code)

Max Activating Token Index: 38

Text #12

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1570484 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.8605. Min Act: -0.0000

Data Index: 807586 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1364189 (Python Code)

Max Activating Token Index: 517

Text #15

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1439930 (Python Code)

Max Activating Token Index: 774

Text #16

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.7255. Min Act: -0.0000

Data Index: 303211 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.7250. Min Act: -0.0000

Data Index: 997652 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1550113 (Python Code)

Max Activating Token Index: 954

Text #19

Max Range: 1.8534. Min Range: -1.8534

Max Act: 0.7163. Min Act: -0.0000

Data Index: 835043 (C4 (Web Text))

Max Activating Token Index: 322