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

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

Neuron 2592 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1255. Min Act: -0.0001

Data Index: 506648 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1229. Min Act: -0.0001

Data Index: 251204 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1184. Min Act: -0.0001

Data Index: 402662 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1311. Min Act: -0.0001

Data Index: 517711 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1357606 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1231. Min Act: -0.0001

Data Index: 267995 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1128. Min Act: -0.0000

Data Index: 955819 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1154. Min Act: -0.0001

Data Index: 737853 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1112. Min Act: -0.0000

Data Index: 952675 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1243488 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1117041 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1319521 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1028. Min Act: -0.0001

Data Index: 785780 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1058. Min Act: -0.0001

Data Index: 1334208 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1078321 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1092. Min Act: -0.0001

Data Index: 407450 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1025. Min Act: -0.0000

Data Index: 138380 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.1021. Min Act: -0.0001

Data Index: 52015 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1190189 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.1311. Min Range: -0.1311

Max Act: 0.0966. Min Act: -0.0001

Data Index: 625913 (C4 (Web Text))

Max Activating Token Index: 702