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

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

Neuron 5211 in Layer 1

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: 0.0045. Min Range: -0.0045

Max Act: 0.0045. Min Act: -0.0002

Data Index: 749975 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0039. Min Act: -0.0002

Data Index: 547047 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0038. Min Act: -0.0002

Data Index: 625843 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1319144 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0032. Min Act: -0.0002

Data Index: 682221 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0031. Min Act: -0.0002

Data Index: 1278832 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0032. Min Act: -0.0002

Data Index: 940402 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0031. Min Act: -0.0002

Data Index: 740931 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0030. Min Act: -0.0001

Data Index: 1067378 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0030. Min Act: -0.0002

Data Index: 857156 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0030. Min Act: -0.0002

Data Index: 711156 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0029. Min Act: -0.0002

Data Index: 646564 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0029. Min Act: -0.0002

Data Index: 1336371 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0029. Min Act: -0.0002

Data Index: 938510 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0028. Min Act: -0.0002

Data Index: 1322184 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0029. Min Act: -0.0002

Data Index: 828530 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0029. Min Act: -0.0002

Data Index: 519535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0028. Min Act: -0.0003

Data Index: 242382 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0028. Min Act: -0.0002

Data Index: 1546697 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0045. Min Range: -0.0045

Max Act: 0.0028. Min Act: -0.0002

Data Index: 1452363 (Python Code)

Max Activating Token Index: 1023