Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 127 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0003

Data Index: 931170 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0993. Min Act: -0.0003

Data Index: 1247517 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0982. Min Act: -0.0003

Data Index: 154818 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0934. Min Act: -0.0004

Data Index: 386663 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0878. Min Act: -0.0004

Data Index: 939667 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0937. Min Act: -0.0003

Data Index: 1054996 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0916. Min Act: -0.0003

Data Index: 1349277 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0903. Min Act: -0.0003

Data Index: 427438 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0886. Min Act: -0.0003

Data Index: 350627 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0918. Min Act: -0.0004

Data Index: 1230608 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0890. Min Act: -0.0003

Data Index: 50511 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0892. Min Act: -0.0003

Data Index: 236287 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0892. Min Act: -0.0003

Data Index: 462489 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0887. Min Act: -0.0003

Data Index: 38652 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0846. Min Act: -0.0003

Data Index: 523070 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0842. Min Act: -0.0003

Data Index: 529855 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0872. Min Act: -0.0004

Data Index: 591818 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0874. Min Act: -0.0003

Data Index: 831989 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0870. Min Act: -0.0003

Data Index: 1037389 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0832. Min Act: -0.0004

Data Index: 1288808 (C4 (Web Text))

Max Activating Token Index: 340