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

Dataset: The Pile

Neuron 4399 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.8606. Min Act: -0.0000

Data Index: 724503 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.8344. Min Act: -0.0000

Data Index: 357750 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.8180. Min Act: -0.0000

Data Index: 1535035 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6052. Min Act: -0.0000

Data Index: 1037963 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4920. Min Act: -0.0000

Data Index: 1493198 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5140. Min Act: -0.0000

Data Index: 819500 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5105. Min Act: -0.0000

Data Index: 1893096 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4555. Min Act: -0.0000

Data Index: 1875195 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3306. Min Act: -0.0000

Data Index: 278723 (The Pile)

Max Activating Token Index: 33

Text #9

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1578199 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5240. Min Act: -0.0000

Data Index: 1206862 (The Pile)

Max Activating Token Index: 197

Text #11

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3750. Min Act: -0.0000

Data Index: 1000578 (The Pile)

Max Activating Token Index: 441

Text #12

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4893. Min Act: -0.0000

Data Index: 757870 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4779. Min Act: -0.0000

Data Index: 1704179 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1985581 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.2999. Min Act: -0.0000

Data Index: 322053 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3412. Min Act: -0.0000

Data Index: 15382 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.3754. Min Act: -0.0000

Data Index: 1303298 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1135117 (The Pile)

Max Activating Token Index: 116

Text #19

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.2284. Min Act: -0.0000

Data Index: 474024 (The Pile)

Max Activating Token Index: 949