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

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

Neuron 4253 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2454. Min Range: -1.2454

Max Act: 1.2454. Min Act: -0.0002

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9322. Min Act: -0.0002

Data Index: 787944 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9295. Min Act: -0.0002

Data Index: 129660 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9761. Min Act: -0.0002

Data Index: 1258824 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9029. Min Act: -0.0002

Data Index: 409281 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 1.2454. Min Range: -1.2454

Max Act: 1.0200. Min Act: -0.0002

Data Index: 502664 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9557. Min Act: -0.0002

Data Index: 682277 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9773. Min Act: -0.0002

Data Index: 132498 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9980. Min Act: -0.0002

Data Index: 1333051 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.7458. Min Act: -0.0002

Data Index: 1307757 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.8603. Min Act: -0.0002

Data Index: 998467 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9008. Min Act: -0.0002

Data Index: 15335 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.8631. Min Act: -0.0002

Data Index: 594099 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9361. Min Act: -0.0002

Data Index: 340117 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.8167. Min Act: -0.0002

Data Index: 1008775 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.8673. Min Act: -0.0002

Data Index: 434094 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.9067. Min Act: -0.0002

Data Index: 1162760 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.7743. Min Act: -0.0002

Data Index: 499420 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.8109. Min Act: -0.0002

Data Index: 356031 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 1.2454. Min Range: -1.2454

Max Act: 0.8327. Min Act: -0.0002

Data Index: 854204 (C4 (Web Text))

Max Activating Token Index: 801