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

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

Neuron 2535 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3911. Min Act: -0.0000

Data Index: 645318 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1547308 (Python Code)

Max Activating Token Index: 636

Text #2

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1538614 (Python Code)

Max Activating Token Index: 655

Text #3

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3082. Min Act: -0.0000

Data Index: 1627689 (Python Code)

Max Activating Token Index: 752

Text #4

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1244051 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1516923 (Python Code)

Max Activating Token Index: 285

Text #6

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1569498 (Python Code)

Max Activating Token Index: 253

Text #7

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1534151 (Python Code)

Max Activating Token Index: 744

Text #8

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3135. Min Act: -0.0000

Data Index: 491943 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1453443 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1280260 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1290251 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2735. Min Act: 0.0000

Data Index: 93229 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2806. Min Act: -0.0000

Data Index: 798103 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1625034 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.3075. Min Act: -0.0000

Data Index: 20351 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2709. Min Act: -0.0000

Data Index: 701147 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2736. Min Act: 0.0000

Data Index: 1152317 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2626. Min Act: -0.0000

Data Index: 475071 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.3911. Min Range: -0.3911

Max Act: 0.2559. Min Act: -0.0000

Data Index: 895062 (C4 (Web Text))

Max Activating Token Index: 419