Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5007 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.2052. Min Act: -0.0002

Data Index: 751929 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1616. Min Act: -0.0002

Data Index: 722358 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1563. Min Act: -0.0002

Data Index: 164805 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1569. Min Act: -0.0002

Data Index: 829212 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1459. Min Act: -0.0002

Data Index: 1335843 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1435. Min Act: -0.0002

Data Index: 215897 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1524. Min Act: -0.0002

Data Index: 1217639 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1329. Min Act: -0.0002

Data Index: 681729 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1277. Min Act: -0.0002

Data Index: 616380 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1288. Min Act: -0.0002

Data Index: 634847 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1282. Min Act: -0.0002

Data Index: 741355 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1481. Min Act: -0.0002

Data Index: 286375 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1135. Min Act: -0.0002

Data Index: 820005 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1010951 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1213. Min Act: -0.0002

Data Index: 572466 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1226. Min Act: -0.0002

Data Index: 8160 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1079704 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1281. Min Act: -0.0002

Data Index: 755777 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1295017 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.2052. Min Range: -0.2052

Max Act: 0.1146. Min Act: -0.0002

Data Index: 449532 (C4 (Web Text))

Max Activating Token Index: 526