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

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

Neuron 2781 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1565676 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1474161 (Python Code)

Max Activating Token Index: 783

Text #2

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1441881 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1430760 (Python Code)

Max Activating Token Index: 632

Text #4

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1085. Min Act: -0.0000

Data Index: 1423608 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1653061 (Python Code)

Max Activating Token Index: 258

Text #6

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1506789 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1488937 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1618970 (Python Code)

Max Activating Token Index: 340

Text #9

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0950. Min Act: -0.0000

Data Index: 250315 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0896. Min Act: -0.0000

Data Index: 195219 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0897. Min Act: -0.0000

Data Index: 335613 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1157251 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0861. Min Act: -0.0000

Data Index: 960199 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1539627 (Python Code)

Max Activating Token Index: 702

Text #15

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0838. Min Act: -0.0000

Data Index: 883942 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1378431 (Python Code)

Max Activating Token Index: 988

Text #17

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1608400 (Python Code)

Max Activating Token Index: 193

Text #18

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1192188 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1250530 (C4 (Web Text))

Max Activating Token Index: 277