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

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

Neuron 895 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6143. Min Range: -3.6143

Max Act: 3.6143. Min Act: -0.0000

Data Index: 1360789 (Python Code)

Max Activating Token Index: 792

Text #1

Max Range: 3.6143. Min Range: -3.6143

Max Act: 3.0681. Min Act: -0.0000

Data Index: 1579663 (Python Code)

Max Activating Token Index: 855

Text #2

Max Range: 3.6143. Min Range: -3.6143

Max Act: 3.1194. Min Act: -0.0000

Data Index: 1625454 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.9704. Min Act: -0.0000

Data Index: 1446553 (Python Code)

Max Activating Token Index: 504

Text #4

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.9500. Min Act: -0.0000

Data Index: 1437116 (Python Code)

Max Activating Token Index: 847

Text #5

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.9341. Min Act: -0.0000

Data Index: 1380428 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.9041. Min Act: -0.0000

Data Index: 1454985 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.8845. Min Act: -0.0000

Data Index: 1591319 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.6948. Min Act: -0.0000

Data Index: 1429082 (Python Code)

Max Activating Token Index: 275

Text #9

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.7925. Min Act: -0.0000

Data Index: 1625660 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.8022. Min Act: -0.0000

Data Index: 1511630 (Python Code)

Max Activating Token Index: 345

Text #11

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.9512. Min Act: -0.0000

Data Index: 1567914 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.7649. Min Act: -0.0000

Data Index: 1480395 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.8974. Min Act: -0.0000

Data Index: 1459857 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.8232. Min Act: -0.0000

Data Index: 1440654 (Python Code)

Max Activating Token Index: 516

Text #15

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.6716. Min Act: -0.0000

Data Index: 1470419 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.7726. Min Act: -0.0000

Data Index: 1397952 (Python Code)

Max Activating Token Index: 514

Text #17

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.4498. Min Act: -0.0000

Data Index: 1601018 (Python Code)

Max Activating Token Index: 324

Text #18

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.8327. Min Act: -0.0000

Data Index: 1489170 (Python Code)

Max Activating Token Index: 241

Text #19

Max Range: 3.6143. Min Range: -3.6143

Max Act: 2.5451. Min Act: -0.0000

Data Index: 1373400 (Python Code)

Max Activating Token Index: 902