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

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

Neuron 3389 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0246. Min Range: -1.0246

Max Act: 1.0246. Min Act: -0.0000

Data Index: 1190257 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1251569 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8906. Min Act: -0.0000

Data Index: 663532 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8559. Min Act: -0.0000

Data Index: 798930 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.9424. Min Act: -0.0000

Data Index: 509285 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8735. Min Act: -0.0000

Data Index: 541370 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.9068. Min Act: -0.0000

Data Index: 160950 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7470. Min Act: -0.0000

Data Index: 1051802 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8601. Min Act: -0.0000

Data Index: 389544 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8263. Min Act: -0.0000

Data Index: 417217 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7885. Min Act: -0.0000

Data Index: 42798 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7898. Min Act: -0.0000

Data Index: 408989 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8195. Min Act: -0.0000

Data Index: 744067 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7492. Min Act: -0.0000

Data Index: 75296 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8005. Min Act: -0.0000

Data Index: 412654 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7425. Min Act: -0.0000

Data Index: 11889 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1040389 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7899. Min Act: -0.0000

Data Index: 504058 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1072760 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.0246. Min Range: -1.0246

Max Act: 0.7575. Min Act: -0.0000

Data Index: 17374 (C4 (Web Text))

Max Activating Token Index: 122