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

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

Neuron 4265 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7749. Min Act: -0.0002

Data Index: 738061 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.7037. Min Act: -0.0002

Data Index: 652623 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6732. Min Act: -0.0002

Data Index: 1230858 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6146. Min Act: -0.0002

Data Index: 70219 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6061. Min Act: -0.0002

Data Index: 267078 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6184. Min Act: -0.0002

Data Index: 1253691 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5954. Min Act: -0.0002

Data Index: 692488 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6112. Min Act: -0.0002

Data Index: 990303 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5837. Min Act: -0.0002

Data Index: 341739 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5972. Min Act: -0.0002

Data Index: 565002 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5994. Min Act: -0.0002

Data Index: 204756 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5900. Min Act: -0.0002

Data Index: 785029 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6090. Min Act: -0.0002

Data Index: 857855 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.6040. Min Act: -0.0002

Data Index: 305768 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5628. Min Act: -0.0002

Data Index: 616052 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5793. Min Act: -0.0002

Data Index: 823986 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5517. Min Act: -0.0002

Data Index: 1295411 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5761. Min Act: -0.0002

Data Index: 1019596 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5320. Min Act: -0.0002

Data Index: 1010267 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.7749. Min Range: -0.7749

Max Act: 0.5341. Min Act: -0.0002

Data Index: 1145915 (C4 (Web Text))

Max Activating Token Index: 256