Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 258 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1309892 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7374. Min Act: -0.0001

Data Index: 1283377 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7290. Min Act: -0.0001

Data Index: 559011 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7045. Min Act: -0.0001

Data Index: 639018 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7409. Min Act: -0.0001

Data Index: 481949 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6919. Min Act: -0.0001

Data Index: 62479 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7138. Min Act: -0.0001

Data Index: 1308499 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6857. Min Act: -0.0001

Data Index: 1233949 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7032. Min Act: -0.0001

Data Index: 42825 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7015. Min Act: -0.0001

Data Index: 73531 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7018. Min Act: -0.0001

Data Index: 274753 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7015. Min Act: -0.0001

Data Index: 1112119 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7023. Min Act: -0.0001

Data Index: 1229546 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.7011. Min Act: -0.0001

Data Index: 998919 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6996. Min Act: -0.0001

Data Index: 979028 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6987. Min Act: -0.0001

Data Index: 123968 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6756. Min Act: -0.0001

Data Index: 504307 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6725. Min Act: -0.0001

Data Index: 1355682 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6929. Min Act: -0.0001

Data Index: 360433 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.7737. Min Range: -0.7737

Max Act: 0.6699. Min Act: -0.0001

Data Index: 211677 (C4 (Web Text))

Max Activating Token Index: 994