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

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

Neuron 3936 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: 2.9431. Min Range: -2.9431

Max Act: 2.9431. Min Act: -0.0000

Data Index: 1439624 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.6894. Min Act: -0.0000

Data Index: 1571477 (Python Code)

Max Activating Token Index: 687

Text #2

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.2521. Min Act: -0.0000

Data Index: 1490729 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.3916. Min Act: -0.0000

Data Index: 1519203 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.3754. Min Act: -0.0000

Data Index: 1486061 (Python Code)

Max Activating Token Index: 663

Text #5

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.3465. Min Act: -0.0000

Data Index: 1473918 (Python Code)

Max Activating Token Index: 127

Text #6

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.2119. Min Act: -0.0000

Data Index: 1507666 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.1799. Min Act: -0.0000

Data Index: 1419820 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.0502. Min Act: -0.0000

Data Index: 1532438 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.2465. Min Act: -0.0000

Data Index: 1382014 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.1067. Min Act: -0.0000

Data Index: 1521287 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.0547. Min Act: -0.0000

Data Index: 1584470 (Python Code)

Max Activating Token Index: 473

Text #12

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.0588. Min Act: -0.0000

Data Index: 1470440 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.1560. Min Act: -0.0000

Data Index: 1370068 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.0321. Min Act: -0.0000

Data Index: 1480295 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.1455. Min Act: -0.0000

Data Index: 1543400 (Python Code)

Max Activating Token Index: 541

Text #16

Max Range: 2.9431. Min Range: -2.9431

Max Act: 2.0195. Min Act: -0.0000

Data Index: 1473922 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 2.9431. Min Range: -2.9431

Max Act: 1.9971. Min Act: -0.0000

Data Index: 1502535 (Python Code)

Max Activating Token Index: 518

Text #18

Max Range: 2.9431. Min Range: -2.9431

Max Act: 1.9877. Min Act: -0.0000

Data Index: 1532615 (Python Code)

Max Activating Token Index: 720

Text #19

Max Range: 2.9431. Min Range: -2.9431

Max Act: 1.9814. Min Act: -0.0000

Data Index: 1550100 (Python Code)

Max Activating Token Index: 683