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

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

Neuron 560 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.6195. Min Act: -0.0000

Data Index: 864163 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5970. Min Act: -0.0000

Data Index: 657973 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.6049. Min Act: -0.0000

Data Index: 113380 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5572. Min Act: -0.0000

Data Index: 1271995 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5776. Min Act: -0.0000

Data Index: 956976 (C4 (Web Text))

Max Activating Token Index: 542

Text #5

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5350. Min Act: -0.0000

Data Index: 447368 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1274097 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4796. Min Act: -0.0000

Data Index: 954837 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5518. Min Act: -0.0000

Data Index: 383197 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5585. Min Act: -0.0000

Data Index: 236105 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5474. Min Act: -0.0000

Data Index: 554054 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5663. Min Act: -0.0000

Data Index: 657580 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5221. Min Act: -0.0000

Data Index: 270416 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4568. Min Act: -0.0000

Data Index: 234953 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.5186. Min Act: -0.0000

Data Index: 547538 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4697. Min Act: -0.0000

Data Index: 834009 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4497. Min Act: -0.0000

Data Index: 966078 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4453. Min Act: -0.0000

Data Index: 30100 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1295842 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.6195. Min Range: -0.6195

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1275264 (C4 (Web Text))

Max Activating Token Index: 816