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

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

Neuron 1465 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4624. Min Range: -2.4624

Max Act: 2.4624. Min Act: -0.0000

Data Index: 55213 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 2.4624. Min Range: -2.4624

Max Act: 2.2345. Min Act: -0.0000

Data Index: 667257 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 2.4624. Min Range: -2.4624

Max Act: 2.1234. Min Act: -0.0000

Data Index: 1249904 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 2.4624. Min Range: -2.4624

Max Act: 2.0404. Min Act: -0.0000

Data Index: 464919 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 2.4624. Min Range: -2.4624

Max Act: 2.0101. Min Act: -0.0000

Data Index: 19787 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8930. Min Act: -0.0000

Data Index: 44285 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.9375. Min Act: -0.0000

Data Index: 944511 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8079. Min Act: -0.0000

Data Index: 1347735 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 2.4624. Min Range: -2.4624

Max Act: 2.0290. Min Act: -0.0001

Data Index: 818465 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8056. Min Act: -0.0000

Data Index: 931686 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.7780. Min Act: -0.0000

Data Index: 605141 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8713. Min Act: -0.0000

Data Index: 364768 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8914. Min Act: -0.0000

Data Index: 1200415 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8664. Min Act: -0.0001

Data Index: 315266 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8499. Min Act: -0.0000

Data Index: 989827 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8416. Min Act: -0.0000

Data Index: 324617 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8235. Min Act: -0.0001

Data Index: 1105733 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.8102. Min Act: -0.0000

Data Index: 769571 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.7089. Min Act: -0.0000

Data Index: 658100 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 2.4624. Min Range: -2.4624

Max Act: 1.7893. Min Act: -0.0000

Data Index: 409749 (C4 (Web Text))

Max Activating Token Index: 86