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

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

Neuron 4658 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: 0.6006. Min Range: -0.6006

Max Act: 0.6006. Min Act: -0.0000

Data Index: 342795 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5642. Min Act: -0.0000

Data Index: 645969 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5451. Min Act: -0.0000

Data Index: 225296 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5346. Min Act: -0.0000

Data Index: 99400 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1350806 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5519. Min Act: -0.0000

Data Index: 688313 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5204. Min Act: -0.0000

Data Index: 633735 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4720. Min Act: -0.0000

Data Index: 668741 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4632. Min Act: -0.0000

Data Index: 100220 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4876. Min Act: -0.0000

Data Index: 729263 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4497. Min Act: -0.0000

Data Index: 203938 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1281756 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4233. Min Act: -0.0000

Data Index: 401025 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4578. Min Act: -0.0000

Data Index: 711415 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4427. Min Act: -0.0000

Data Index: 420857 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4673. Min Act: -0.0000

Data Index: 657534 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4174. Min Act: -0.0000

Data Index: 231072 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1013530 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1020987 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1207419 (C4 (Web Text))

Max Activating Token Index: 993