Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 617 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0000

Data Index: 991292 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1337. Min Act: -0.0000

Data Index: 269501 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1354. Min Act: -0.0000

Data Index: 495722 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1089617 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1279. Min Act: -0.0000

Data Index: 305323 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1299. Min Act: -0.0000

Data Index: 590626 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1308306 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1126924 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1239. Min Act: -0.0000

Data Index: 531686 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1177. Min Act: -0.0000

Data Index: 494733 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1153863 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1240. Min Act: -0.0000

Data Index: 396463 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1141. Min Act: -0.0000

Data Index: 13351 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1135. Min Act: -0.0000

Data Index: 604760 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1170. Min Act: -0.0000

Data Index: 913431 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1081. Min Act: -0.0000

Data Index: 397363 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1078777 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1071. Min Act: -0.0000

Data Index: 988358 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1061. Min Act: -0.0000

Data Index: 118304 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1065. Min Act: -0.0000

Data Index: 508811 (C4 (Web Text))

Max Activating Token Index: 784