Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3726 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1561555 (Python Code)

Max Activating Token Index: 577

Text #1

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1589832 (Python Code)

Max Activating Token Index: 666

Text #2

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1363178 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5938. Min Act: -0.0000

Data Index: 339693 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5372. Min Act: -0.0000

Data Index: 308170 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1499937 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5109. Min Act: -0.0000

Data Index: 836125 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1553202 (Python Code)

Max Activating Token Index: 333

Text #8

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5104. Min Act: -0.0000

Data Index: 1626671 (Python Code)

Max Activating Token Index: 736

Text #9

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1391961 (Python Code)

Max Activating Token Index: 242

Text #10

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1591117 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1376917 (Python Code)

Max Activating Token Index: 735

Text #12

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1635541 (Python Code)

Max Activating Token Index: 865

Text #13

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1595982 (Python Code)

Max Activating Token Index: 378

Text #14

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1589216 (Python Code)

Max Activating Token Index: 868

Text #15

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.4687. Min Act: 0.0000

Data Index: 573808 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.4053. Min Act: 0.0000

Data Index: 868847 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1602292 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1314110 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.8159. Min Range: -0.8159

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1618339 (Python Code)

Max Activating Token Index: 184