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

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

Neuron 880 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: 0.2135. Min Range: -0.2135

Max Act: 0.2135. Min Act: -0.0001

Data Index: 173119 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1767. Min Act: -0.0001

Data Index: 1257622 (C4 (Web Text))

Max Activating Token Index: 267

Text #2

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1708. Min Act: -0.0001

Data Index: 500693 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1417. Min Act: -0.0001

Data Index: 879210 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1576. Min Act: -0.0001

Data Index: 1067350 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1437. Min Act: -0.0001

Data Index: 1326258 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1489. Min Act: -0.0001

Data Index: 100839 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1385. Min Act: -0.0001

Data Index: 884961 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1431. Min Act: -0.0001

Data Index: 907742 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1344. Min Act: -0.0001

Data Index: 76168 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1323. Min Act: -0.0001

Data Index: 554189 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1368. Min Act: -0.0001

Data Index: 416034 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1285554 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1227. Min Act: -0.0001

Data Index: 301386 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1178. Min Act: -0.0001

Data Index: 44485 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1250. Min Act: -0.0001

Data Index: 1064057 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1330. Min Act: -0.0001

Data Index: 132562 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1194. Min Act: -0.0001

Data Index: 392605 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1099. Min Act: -0.0001

Data Index: 444636 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.2135. Min Range: -0.2135

Max Act: 0.1092. Min Act: -0.0001

Data Index: 703826 (C4 (Web Text))

Max Activating Token Index: 957