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

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

Neuron 1228 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8892. Min Act: -0.0000

Data Index: 323448 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6880. Min Act: -0.0000

Data Index: 367276 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6361. Min Act: -0.0000

Data Index: 881151 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1449992 (Python Code)

Max Activating Token Index: 649

Text #4

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6230. Min Act: -0.0000

Data Index: 29665 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1053369 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1648886 (Python Code)

Max Activating Token Index: 249

Text #7

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5507. Min Act: -0.0000

Data Index: 128025 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1150994 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5545. Min Act: -0.0000

Data Index: 350873 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5271. Min Act: -0.0000

Data Index: 463499 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5290. Min Act: -0.0000

Data Index: 771428 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1174417 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5136. Min Act: -0.0000

Data Index: 707745 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.4944. Min Act: -0.0000

Data Index: 681044 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.5041. Min Act: -0.0000

Data Index: 811821 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1256012 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.4778. Min Act: -0.0000

Data Index: 915069 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1410504 (Python Code)

Max Activating Token Index: 892

Text #19

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1254810 (C4 (Web Text))

Max Activating Token Index: 35