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

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

Neuron 4507 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: 1.9465. Min Range: -1.9465

Max Act: 1.9367. Min Act: -0.0000

Data Index: 69901 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.9465. Min Act: -0.0000

Data Index: 200755 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5806. Min Act: -0.0000

Data Index: 524275 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5554. Min Act: -0.0000

Data Index: 127050 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5991. Min Act: -0.0000

Data Index: 257495 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.6805. Min Act: -0.0000

Data Index: 319480 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.6043. Min Act: -0.0000

Data Index: 961327 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1047971 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5118. Min Act: -0.0000

Data Index: 667793 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4448. Min Act: -0.0000

Data Index: 658364 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5933. Min Act: -0.0000

Data Index: 276454 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5330. Min Act: -0.0000

Data Index: 438469 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4276. Min Act: -0.0000

Data Index: 692698 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5091. Min Act: -0.0000

Data Index: 805709 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4912. Min Act: -0.0000

Data Index: 627641 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4935. Min Act: -0.0000

Data Index: 354766 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4522. Min Act: -0.0000

Data Index: 930122 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.3372. Min Act: -0.0000

Data Index: 189222 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1229035 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.9465. Min Range: -1.9465

Max Act: 1.5495. Min Act: -0.0000

Data Index: 959045 (C4 (Web Text))

Max Activating Token Index: 152