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

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

Neuron 3213 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3971. Min Act: -0.0000

Data Index: 1529396 (Python Code)

Max Activating Token Index: 822

Text #1

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1432742 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3609. Min Act: -0.0000

Data Index: 211108 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1497875 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1428810 (Python Code)

Max Activating Token Index: 501

Text #5

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3401. Min Act: 0.0000

Data Index: 1574847 (Python Code)

Max Activating Token Index: 814

Text #6

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3263. Min Act: -0.0000

Data Index: 1439081 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3411. Min Act: -0.0000

Data Index: 873590 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3246. Min Act: -0.0000

Data Index: 1304016 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1406856 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1536238 (Python Code)

Max Activating Token Index: 637

Text #11

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1501423 (Python Code)

Max Activating Token Index: 53

Text #12

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1363087 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1542823 (Python Code)

Max Activating Token Index: 193

Text #14

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1646560 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2701. Min Act: -0.0000

Data Index: 1629965 (Python Code)

Max Activating Token Index: 562

Text #16

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2879. Min Act: -0.0000

Data Index: 805088 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2816. Min Act: -0.0000

Data Index: 504104 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1575003 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.3971. Min Range: -0.3971

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1382804 (Python Code)

Max Activating Token Index: 279