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

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

Neuron 4048 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1764. Min Act: -0.0001

Data Index: 942445 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1617. Min Act: -0.0000

Data Index: 396421 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1478. Min Act: -0.0001

Data Index: 48506 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1269269 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1460. Min Act: -0.0000

Data Index: 672310 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1314. Min Act: -0.0001

Data Index: 22017 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1277. Min Act: -0.0000

Data Index: 320117 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1137. Min Act: -0.0001

Data Index: 501824 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1269. Min Act: -0.0001

Data Index: 196248 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1215. Min Act: -0.0000

Data Index: 297642 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1135. Min Act: -0.0001

Data Index: 272692 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1254. Min Act: -0.0001

Data Index: 187921 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1189. Min Act: -0.0001

Data Index: 196453 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1207. Min Act: -0.0001

Data Index: 514510 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.0997. Min Act: -0.0001

Data Index: 67013 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1200. Min Act: -0.0001

Data Index: 571723 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1083. Min Act: -0.0001

Data Index: 595826 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1144. Min Act: -0.0001

Data Index: 917020 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1192. Min Act: -0.0001

Data Index: 443869 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.1764. Min Range: -0.1764

Max Act: 0.1204. Min Act: -0.0001

Data Index: 987040 (C4 (Web Text))

Max Activating Token Index: 227