Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2299 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.7140. Min Act: -0.0003

Data Index: 1647572 (Python Code)

Max Activating Token Index: 1011

Text #1

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6942. Min Act: -0.0003

Data Index: 1363575 (Python Code)

Max Activating Token Index: 1008

Text #2

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6372. Min Act: -0.0003

Data Index: 1643186 (Python Code)

Max Activating Token Index: 482

Text #3

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6299. Min Act: -0.0003

Data Index: 1600702 (Python Code)

Max Activating Token Index: 1017

Text #4

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.6005. Min Act: -0.0003

Data Index: 1589835 (Python Code)

Max Activating Token Index: 1012

Text #5

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5915. Min Act: -0.0003

Data Index: 1563036 (Python Code)

Max Activating Token Index: 839

Text #6

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5910. Min Act: -0.0004

Data Index: 777681 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5861. Min Act: -0.0003

Data Index: 1655319 (Python Code)

Max Activating Token Index: 834

Text #8

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5773. Min Act: -0.0003

Data Index: 1563760 (Python Code)

Max Activating Token Index: 1000

Text #9

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5963. Min Act: -0.0003

Data Index: 1389241 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5647. Min Act: -0.0003

Data Index: 1647388 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5608. Min Act: -0.0003

Data Index: 1572745 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5548. Min Act: -0.0003

Data Index: 1415100 (Python Code)

Max Activating Token Index: 867

Text #13

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5495. Min Act: -0.0003

Data Index: 1524410 (Python Code)

Max Activating Token Index: 581

Text #14

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5488. Min Act: -0.0003

Data Index: 1614304 (Python Code)

Max Activating Token Index: 451

Text #15

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5384. Min Act: -0.0003

Data Index: 1408227 (Python Code)

Max Activating Token Index: 1020

Text #16

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5311. Min Act: -0.0003

Data Index: 1374156 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5281. Min Act: -0.0003

Data Index: 1553656 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5265. Min Act: -0.0003

Data Index: 1605174 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 0.7140. Min Range: -0.7140

Max Act: 0.5249. Min Act: -0.0003

Data Index: 1648525 (Python Code)

Max Activating Token Index: 740