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

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

Neuron 570 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0001

Data Index: 367981 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0860. Min Act: -0.0001

Data Index: 268121 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0912. Min Act: -0.0001

Data Index: 608938 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0950. Min Act: -0.0001

Data Index: 210894 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0945. Min Act: -0.0001

Data Index: 604549 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0880. Min Act: -0.0001

Data Index: 140314 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0920. Min Act: -0.0001

Data Index: 820183 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1501599 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1430396 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0880. Min Act: -0.0001

Data Index: 409167 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1455229 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0854. Min Act: -0.0001

Data Index: 954823 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1428723 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0854. Min Act: -0.0001

Data Index: 642280 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0847. Min Act: -0.0001

Data Index: 408362 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0804. Min Act: -0.0001

Data Index: 978654 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1141499 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0825. Min Act: -0.0001

Data Index: 729921 (C4 (Web Text))

Max Activating Token Index: 809

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0900. Min Act: -0.0001

Data Index: 871007 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1347051 (C4 (Web Text))

Max Activating Token Index: 414