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

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

Neuron 41 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0009. Min Range: -1.0009

Max Act: 1.0009. Min Act: -0.0001

Data Index: 725375 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9858. Min Act: -0.0001

Data Index: 604574 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8588. Min Act: -0.0001

Data Index: 1101947 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8803. Min Act: -0.0001

Data Index: 1564415 (Python Code)

Max Activating Token Index: 457

Text #4

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9363. Min Act: -0.0001

Data Index: 1639590 (Python Code)

Max Activating Token Index: 559

Text #5

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8096. Min Act: -0.0001

Data Index: 960800 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1631625 (Python Code)

Max Activating Token Index: 421

Text #7

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.9514. Min Act: -0.0000

Data Index: 518556 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1056155 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8337. Min Act: -0.0001

Data Index: 921050 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8148. Min Act: -0.0001

Data Index: 1513986 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.7494. Min Act: -0.0001

Data Index: 263291 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.7926. Min Act: -0.0001

Data Index: 1535859 (Python Code)

Max Activating Token Index: 616

Text #13

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1519719 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.7620. Min Act: -0.0001

Data Index: 1465762 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.6623. Min Act: -0.0001

Data Index: 1537561 (Python Code)

Max Activating Token Index: 156

Text #16

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.7538. Min Act: -0.0001

Data Index: 169139 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.7456. Min Act: -0.0001

Data Index: 961285 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.7890. Min Act: -0.0001

Data Index: 1569974 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 1.0009. Min Range: -1.0009

Max Act: 0.7430. Min Act: -0.0001

Data Index: 1599764 (Python Code)

Max Activating Token Index: 64