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

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

Neuron 2433 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: 1.1126. Min Range: -1.1126

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1330847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0758. Min Act: -0.0001

Data Index: 1358464 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0606. Min Act: -0.0001

Data Index: 304999 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0647. Min Act: -0.0001

Data Index: 908095 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0648. Min Act: -0.0001

Data Index: 1137634 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0616. Min Act: -0.0001

Data Index: 405265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0388. Min Act: -0.0001

Data Index: 315190 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0550. Min Act: -0.0001

Data Index: 719330 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0478. Min Act: -0.0001

Data Index: 1010179 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0325. Min Act: -0.0001

Data Index: 439636 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0284. Min Act: -0.0001

Data Index: 236818 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0259. Min Act: -0.0001

Data Index: 600886 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0303. Min Act: -0.0001

Data Index: 763977 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0176. Min Act: -0.0002

Data Index: 1328859 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0333. Min Act: -0.0001

Data Index: 862918 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0123. Min Act: -0.0001

Data Index: 137286 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0376. Min Act: -0.0001

Data Index: 415025 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0112. Min Act: -0.0001

Data Index: 500733 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0078. Min Act: -0.0001

Data Index: 1256054 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0164. Min Act: -0.0001

Data Index: 278783 (C4 (Web Text))

Max Activating Token Index: 127