Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4745 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.5770. Min Act: -0.0000

Data Index: 1430562 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.5689. Min Act: -0.0001

Data Index: 1207471 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.5050. Min Act: -0.0001

Data Index: 140988 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.5884. Min Act: -0.0001

Data Index: 862299 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.5147. Min Act: -0.0001

Data Index: 1586032 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4952. Min Act: -0.0001

Data Index: 717266 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4425. Min Act: -0.0001

Data Index: 1094556 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4270. Min Act: -0.0001

Data Index: 774027 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4982. Min Act: -0.0001

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4160. Min Act: -0.0001

Data Index: 137165 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4509. Min Act: -0.0001

Data Index: 352826 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4393. Min Act: -0.0001

Data Index: 332644 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.3828. Min Act: -0.0001

Data Index: 440429 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.3780. Min Act: -0.0001

Data Index: 891330 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.3214. Min Act: -0.0001

Data Index: 200024 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.3609. Min Act: -0.0001

Data Index: 915651 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4200. Min Act: -0.0001

Data Index: 319120 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4714. Min Act: -0.0001

Data Index: 729865 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.4079. Min Act: -0.0001

Data Index: 1247526 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.3455. Min Act: -0.0001

Data Index: 720962 (C4 (Web Text))

Max Activating Token Index: 759