Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3979 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0458. Min Range: -1.0458

Max Act: 1.0458. Min Act: -0.0000

Data Index: 1541370 (Python Code)

Max Activating Token Index: 963

Text #1

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9096. Min Act: -0.0001

Data Index: 1442049 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.9453. Min Act: -0.0001

Data Index: 1379589 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8908. Min Act: -0.0001

Data Index: 1423689 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8871. Min Act: -0.0001

Data Index: 1585173 (Python Code)

Max Activating Token Index: 467

Text #5

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8804. Min Act: -0.0001

Data Index: 1631439 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8842. Min Act: -0.0001

Data Index: 1624621 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1521421 (Python Code)

Max Activating Token Index: 733

Text #8

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1468687 (Python Code)

Max Activating Token Index: 766

Text #9

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7445. Min Act: -0.0001

Data Index: 1555132 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1451541 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8304. Min Act: -0.0001

Data Index: 1579539 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1551340 (Python Code)

Max Activating Token Index: 235

Text #13

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7703. Min Act: -0.0001

Data Index: 1413308 (Python Code)

Max Activating Token Index: 898

Text #14

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7123. Min Act: -0.0001

Data Index: 1522456 (Python Code)

Max Activating Token Index: 900

Text #15

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7571. Min Act: -0.0001

Data Index: 1400718 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7499. Min Act: -0.0001

Data Index: 1608403 (Python Code)

Max Activating Token Index: 803

Text #17

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.6815. Min Act: -0.0001

Data Index: 1539741 (Python Code)

Max Activating Token Index: 215

Text #18

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7528. Min Act: -0.0001

Data Index: 1596522 (Python Code)

Max Activating Token Index: 306

Text #19

Max Range: 1.0458. Min Range: -1.0458

Max Act: 0.7124. Min Act: -0.0001

Data Index: 1655925 (Python Code)

Max Activating Token Index: 506