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

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

Neuron 4216 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3722. Min Range: -2.3722

Max Act: 2.3722. Min Act: -0.0000

Data Index: 504531 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.9833. Min Act: -0.0000

Data Index: 796938 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.6541. Min Act: -0.0000

Data Index: 687785 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.8403. Min Act: -0.0000

Data Index: 827503 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.8139. Min Act: -0.0000

Data Index: 555580 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.8261. Min Act: -0.0000

Data Index: 766955 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.7082. Min Act: -0.0000

Data Index: 1301789 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.8617. Min Act: -0.0000

Data Index: 247095 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.5636. Min Act: -0.0000

Data Index: 442504 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.7987. Min Act: -0.0000

Data Index: 924613 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.7922. Min Act: -0.0000

Data Index: 121399 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.8706. Min Act: -0.0000

Data Index: 629324 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.6641. Min Act: -0.0000

Data Index: 912173 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.6681. Min Act: -0.0000

Data Index: 1198325 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.6555. Min Act: -0.0000

Data Index: 1283786 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.6187. Min Act: -0.0000

Data Index: 467207 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.6505. Min Act: -0.0000

Data Index: 1092634 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.4040. Min Act: -0.0000

Data Index: 60719 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.3148. Min Act: -0.0000

Data Index: 175461 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 2.3722. Min Range: -2.3722

Max Act: 1.3372. Min Act: -0.0000

Data Index: 938694 (C4 (Web Text))

Max Activating Token Index: 515