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

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

Neuron 6105 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1449361 (Python Code)

Max Activating Token Index: 989

Text #1

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1390728 (Python Code)

Max Activating Token Index: 668

Text #2

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1548774 (Python Code)

Max Activating Token Index: 332

Text #3

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1642389 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.4004. Min Act: -0.0000

Data Index: 929079 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1457865 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1042030 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1367885 (Python Code)

Max Activating Token Index: 359

Text #8

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.3193. Min Act: -0.0000

Data Index: 1639295 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.3308. Min Act: -0.0000

Data Index: 571137 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1557864 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1502306 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.3178. Min Act: -0.0000

Data Index: 198038 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1462059 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.2960. Min Act: 0.0000

Data Index: 822153 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.2723. Min Act: 0.0000

Data Index: 1192698 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1498074 (Python Code)

Max Activating Token Index: 103

Text #17

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.2775. Min Act: -0.0000

Data Index: 1531866 (Python Code)

Max Activating Token Index: 272

Text #18

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1452545 (Python Code)

Max Activating Token Index: 83

Text #19

Max Range: 0.5926. Min Range: -0.5926

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1086181 (C4 (Web Text))

Max Activating Token Index: 545