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

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

Neuron 5472 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1388406 (Python Code)

Max Activating Token Index: 960

Text #1

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1620940 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0474. Min Act: -0.0001

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1520298 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1575383 (Python Code)

Max Activating Token Index: 858

Text #5

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1422976 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0206. Min Act: -0.0001

Data Index: 841048 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0211. Min Act: -0.0001

Data Index: 1643548 (Python Code)

Max Activating Token Index: 941

Text #8

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1212205 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0177. Min Act: -0.0001

Data Index: 1612868 (Python Code)

Max Activating Token Index: 895

Text #10

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1593162 (Python Code)

Max Activating Token Index: 972

Text #11

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0136. Min Act: -0.0002

Data Index: 1647089 (Python Code)

Max Activating Token Index: 674

Text #12

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0137. Min Act: -0.0001

Data Index: 1421588 (Python Code)

Max Activating Token Index: 818

Text #13

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0124. Min Act: -0.0001

Data Index: 1398214 (Python Code)

Max Activating Token Index: 971

Text #14

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0125. Min Act: -0.0001

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1498379 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1481823 (Python Code)

Max Activating Token Index: 921

Text #17

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0098. Min Act: -0.0001

Data Index: 987650 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0097. Min Act: -0.0001

Data Index: 557777 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 0.1733. Min Range: -0.1733

Max Act: 0.0094. Min Act: -0.0001

Data Index: 1154695 (C4 (Web Text))

Max Activating Token Index: 920