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

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

Neuron 3409 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6640. Min Act: -0.0001

Data Index: 1522143 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6352. Min Act: -0.0001

Data Index: 1529406 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1409809 (Python Code)

Max Activating Token Index: 560

Text #3

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5937. Min Act: -0.0001

Data Index: 1590808 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5652. Min Act: -0.0001

Data Index: 1592962 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5549. Min Act: -0.0001

Data Index: 1650396 (Python Code)

Max Activating Token Index: 342

Text #6

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5518. Min Act: -0.0001

Data Index: 1514879 (Python Code)

Max Activating Token Index: 656

Text #7

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5726. Min Act: -0.0001

Data Index: 1484148 (Python Code)

Max Activating Token Index: 815

Text #8

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5411. Min Act: -0.0001

Data Index: 1364621 (Python Code)

Max Activating Token Index: 680

Text #9

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5420. Min Act: -0.0001

Data Index: 1598616 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5177. Min Act: -0.0001

Data Index: 1427262 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5079. Min Act: -0.0001

Data Index: 1479070 (Python Code)

Max Activating Token Index: 164

Text #12

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1434656 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4835. Min Act: -0.0001

Data Index: 1375855 (Python Code)

Max Activating Token Index: 913

Text #14

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5044. Min Act: -0.0001

Data Index: 1487848 (Python Code)

Max Activating Token Index: 584

Text #15

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4875. Min Act: -0.0001

Data Index: 1631883 (Python Code)

Max Activating Token Index: 970

Text #16

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5224. Min Act: -0.0001

Data Index: 1611096 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4970. Min Act: -0.0001

Data Index: 1552458 (Python Code)

Max Activating Token Index: 839

Text #18

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.5148. Min Act: -0.0001

Data Index: 1619085 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 0.6640. Min Range: -0.6640

Max Act: 0.4916. Min Act: -0.0001

Data Index: 1570733 (Python Code)

Max Activating Token Index: 921