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

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

Neuron 4994 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.4405. Min Act: -0.0000

Data Index: 1604118 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1486355 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1371786 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1482251 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1591867 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1564433 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1378629 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1624758 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1517571 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1378964 (Python Code)

Max Activating Token Index: 905

Text #10

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1453610 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1411201 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1418505 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1395571 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1624055 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1364762 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1428776 (Python Code)

Max Activating Token Index: 33

Text #17

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1372375 (Python Code)

Max Activating Token Index: 720

Text #18

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1446654 (Python Code)

Max Activating Token Index: 43

Text #19

Max Range: 0.4405. Min Range: -0.4405

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1416201 (Python Code)

Max Activating Token Index: 404