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

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

Neuron 2732 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.3193. Min Act: -0.0000

Data Index: 1429603 (Python Code)

Max Activating Token Index: 358

Text #1

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.1729. Min Act: -0.0000

Data Index: 251974 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1583098 (Python Code)

Max Activating Token Index: 201

Text #3

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.1911. Min Act: -0.0000

Data Index: 1556981 (Python Code)

Max Activating Token Index: 726

Text #4

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1491158 (Python Code)

Max Activating Token Index: 599

Text #5

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0790. Min Act: -0.0000

Data Index: 316275 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1401516 (Python Code)

Max Activating Token Index: 251

Text #7

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8768. Min Act: -0.0000

Data Index: 160244 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1534211 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1425465 (Python Code)

Max Activating Token Index: 329

Text #10

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8294. Min Act: -0.0000

Data Index: 544967 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1053177 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1379530 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1513610 (Python Code)

Max Activating Token Index: 644

Text #14

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8385. Min Act: -0.0000

Data Index: 1525924 (Python Code)

Max Activating Token Index: 386

Text #15

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1526336 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1582520 (Python Code)

Max Activating Token Index: 632

Text #17

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1390408 (Python Code)

Max Activating Token Index: 207

Text #18

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8670. Min Act: -0.0000

Data Index: 1556470 (Python Code)

Max Activating Token Index: 727

Text #19

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1469171 (Python Code)

Max Activating Token Index: 988