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

Dataset: The Pile

Neuron 4350 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.8152. Min Act: -0.0000

Data Index: 278323 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.8022. Min Act: -0.0000

Data Index: 393960 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.7295. Min Act: -0.0000

Data Index: 839002 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1429062 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1699046 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1222942 (The Pile)

Max Activating Token Index: 738

Text #6

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1600133 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.7194. Min Act: -0.0000

Data Index: 653925 (The Pile)

Max Activating Token Index: 967

Text #8

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1317086 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1417931 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.5635. Min Act: -0.0000

Data Index: 167472 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1898327 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.5124. Min Act: -0.0000

Data Index: 329492 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.5710. Min Act: -0.0000

Data Index: 814078 (The Pile)

Max Activating Token Index: 330

Text #14

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.4813. Min Act: -0.0000

Data Index: 914985 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1973353 (The Pile)

Max Activating Token Index: 287

Text #16

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1889414 (The Pile)

Max Activating Token Index: 155

Text #17

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.3397. Min Act: -0.0000

Data Index: 353257 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.3636. Min Act: -0.0000

Data Index: 617859 (The Pile)

Max Activating Token Index: 892

Text #19

Max Range: 0.8152. Min Range: -0.8152

Max Act: 0.3239. Min Act: -0.0000

Data Index: 194334 (The Pile)

Max Activating Token Index: 270