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

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

Neuron 2335 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.5583. Min Act: -0.0000

Data Index: 1360354 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.7314. Min Act: -0.0001

Data Index: 1612770 (Python Code)

Max Activating Token Index: 182

Text #2

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.7894. Min Act: -0.0000

Data Index: 1362434 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.8562. Min Act: -0.0000

Data Index: 1440989 (Python Code)

Max Activating Token Index: 203

Text #4

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.7475. Min Act: -0.0000

Data Index: 1472575 (Python Code)

Max Activating Token Index: 392

Text #5

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.6685. Min Act: -0.0001

Data Index: 1379966 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.6996. Min Act: -0.0000

Data Index: 1480116 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.6493. Min Act: -0.0001

Data Index: 1611246 (Python Code)

Max Activating Token Index: 725

Text #8

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.5972. Min Act: -0.0001

Data Index: 1652973 (Python Code)

Max Activating Token Index: 205

Text #9

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.6141. Min Act: -0.0000

Data Index: 1480857 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.4282. Min Act: -0.0000

Data Index: 1538547 (Python Code)

Max Activating Token Index: 837

Text #11

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.6751. Min Act: -0.0000

Data Index: 1368688 (Python Code)

Max Activating Token Index: 722

Text #12

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.5946. Min Act: -0.0000

Data Index: 1382899 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.6725. Min Act: -0.0001

Data Index: 1403696 (Python Code)

Max Activating Token Index: 364

Text #14

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.5091. Min Act: -0.0001

Data Index: 1554245 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1551174 (Python Code)

Max Activating Token Index: 646

Text #16

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.5337. Min Act: -0.0001

Data Index: 1620897 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.4871. Min Act: -0.0001

Data Index: 1464811 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1556173 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 1.8562. Min Range: -1.8562

Max Act: 1.4628. Min Act: -0.0001

Data Index: 1417850 (Python Code)

Max Activating Token Index: 270