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

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

Neuron 3625 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1200. Min Act: -0.0000

Data Index: 365849 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1337678 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1115. Min Act: -0.0000

Data Index: 145710 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.1132. Min Act: -0.0000

Data Index: 19775 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0951. Min Act: -0.0000

Data Index: 827508 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0981. Min Act: -0.0000

Data Index: 489247 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1333423 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0939. Min Act: -0.0000

Data Index: 258478 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1075575 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0903. Min Act: -0.0001

Data Index: 1150674 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0850. Min Act: -0.0000

Data Index: 270948 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1154661 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1228850 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1327552 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0825. Min Act: -0.0000

Data Index: 643114 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0775. Min Act: -0.0000

Data Index: 918672 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0741. Min Act: -0.0000

Data Index: 188081 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1185647 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0743. Min Act: -0.0000

Data Index: 563362 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.1200. Min Range: -0.1200

Max Act: 0.0748. Min Act: -0.0000

Data Index: 261039 (C4 (Web Text))

Max Activating Token Index: 210