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

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

Neuron 3347 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1422. Min Act: -0.0001

Data Index: 1592037 (Python Code)

Max Activating Token Index: 491

Text #1

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1252. Min Act: -0.0001

Data Index: 714412 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1435634 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1567926 (Python Code)

Max Activating Token Index: 238

Text #4

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1243. Min Act: -0.0001

Data Index: 399441 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1499294 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1607383 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1465768 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1604526 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1495022 (Python Code)

Max Activating Token Index: 254

Text #10

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1585377 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1646311 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1477284 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1491893 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1502318 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1016. Min Act: -0.0001

Data Index: 457086 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1544473 (Python Code)

Max Activating Token Index: 949

Text #17

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1019. Min Act: -0.0001

Data Index: 158113 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1598395 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.0915. Min Act: -0.0001

Data Index: 1429189 (Python Code)

Max Activating Token Index: 195