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

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

Neuron 3887 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0066. Min Act: -0.0002

Data Index: 732400 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1283752 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 107006 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1025297 (C4 (Web Text))

Max Activating Token Index: 1015

Text #4

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1336800 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1320173 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 345167 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1307354 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0060. Min Act: -0.0002

Data Index: 720854 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 80068 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1283829 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 416024 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 453051 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0059. Min Act: -0.0002

Data Index: 499382 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0002

Data Index: 477117 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1135961 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1305681 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1031899 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0002

Data Index: 594207 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0066. Min Range: -0.0066

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1189747 (C4 (Web Text))

Max Activating Token Index: 1003