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

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

Neuron 3948 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6677. Min Range: -4.6677

Max Act: 4.6543. Min Act: -0.0000

Data Index: 1616347 (Python Code)

Max Activating Token Index: 164

Text #1

Max Range: 4.6677. Min Range: -4.6677

Max Act: 4.4614. Min Act: -0.0000

Data Index: 1452402 (Python Code)

Max Activating Token Index: 64

Text #2

Max Range: 4.6677. Min Range: -4.6677

Max Act: 4.6677. Min Act: -0.0000

Data Index: 1393104 (Python Code)

Max Activating Token Index: 92

Text #3

Max Range: 4.6677. Min Range: -4.6677

Max Act: 4.4847. Min Act: -0.0000

Data Index: 1580818 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 4.6677. Min Range: -4.6677

Max Act: 4.1443. Min Act: -0.0000

Data Index: 1422540 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 4.6677. Min Range: -4.6677

Max Act: 4.2524. Min Act: -0.0000

Data Index: 1376190 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.9112. Min Act: -0.0000

Data Index: 1536552 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.8274. Min Act: -0.0000

Data Index: 1473704 (Python Code)

Max Activating Token Index: 312

Text #8

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.5844. Min Act: -0.0000

Data Index: 1371285 (Python Code)

Max Activating Token Index: 623

Text #9

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.5337. Min Act: -0.0000

Data Index: 1496794 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.8158. Min Act: -0.0000

Data Index: 1642692 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.7809. Min Act: -0.0000

Data Index: 1570332 (Python Code)

Max Activating Token Index: 198

Text #12

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.4032. Min Act: -0.0000

Data Index: 1409832 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.7152. Min Act: -0.0000

Data Index: 1604891 (Python Code)

Max Activating Token Index: 373

Text #14

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.5772. Min Act: -0.0000

Data Index: 1495654 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.5902. Min Act: -0.0000

Data Index: 1581602 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.7127. Min Act: -0.0000

Data Index: 1423265 (Python Code)

Max Activating Token Index: 886

Text #17

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.7303. Min Act: -0.0000

Data Index: 1542780 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.5266. Min Act: -0.0000

Data Index: 1483404 (Python Code)

Max Activating Token Index: 137

Text #19

Max Range: 4.6677. Min Range: -4.6677

Max Act: 3.5137. Min Act: -0.0000

Data Index: 1430971 (Python Code)

Max Activating Token Index: 760