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

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

Neuron 3506 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1611. Min Act: -0.0001

Data Index: 104505 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1311. Min Act: -0.0002

Data Index: 1250384 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1279. Min Act: -0.0001

Data Index: 536616 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1100. Min Act: -0.0002

Data Index: 432534 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1157. Min Act: -0.0001

Data Index: 873196 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1139. Min Act: -0.0001

Data Index: 191503 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1125. Min Act: -0.0002

Data Index: 918662 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1129. Min Act: -0.0001

Data Index: 686666 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1156. Min Act: -0.0001

Data Index: 591145 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1132. Min Act: -0.0001

Data Index: 563384 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1136. Min Act: -0.0002

Data Index: 965710 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1191. Min Act: -0.0001

Data Index: 525879 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1223040 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1085. Min Act: -0.0002

Data Index: 24929 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1081. Min Act: -0.0001

Data Index: 196783 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1017893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1063. Min Act: -0.0001

Data Index: 138621 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1018. Min Act: -0.0002

Data Index: 715079 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1012. Min Act: -0.0001

Data Index: 1078480 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1052. Min Act: -0.0002

Data Index: 903861 (C4 (Web Text))

Max Activating Token Index: 370