Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1920 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1206. Min Act: -0.0002

Data Index: 1252193 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1205001 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1140. Min Act: -0.0002

Data Index: 371116 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1160. Min Act: -0.0002

Data Index: 618451 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1143. Min Act: -0.0002

Data Index: 8421 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1128. Min Act: -0.0002

Data Index: 291556 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1092. Min Act: -0.0002

Data Index: 812127 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1091. Min Act: -0.0002

Data Index: 450585 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1134. Min Act: -0.0002

Data Index: 524448 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1095. Min Act: -0.0002

Data Index: 509666 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1147924 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1053. Min Act: -0.0002

Data Index: 1169511 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1041. Min Act: -0.0002

Data Index: 653001 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1053. Min Act: -0.0002

Data Index: 641253 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1287256 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1176618 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1043. Min Act: -0.0002

Data Index: 1242150 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1035. Min Act: -0.0002

Data Index: 752775 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1043. Min Act: -0.0002

Data Index: 817573 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1006. Min Act: -0.0002

Data Index: 961483 (C4 (Web Text))

Max Activating Token Index: 862