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

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

Neuron 2255 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0000

Data Index: 296136 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0792. Min Act: 0.0000

Data Index: 832570 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0621. Min Act: -0.0000

Data Index: 262919 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0591. Min Act: -0.0000

Data Index: 730810 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0567. Min Act: 0.0001

Data Index: 1581978 (Python Code)

Max Activating Token Index: 851

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0575. Min Act: -0.0000

Data Index: 714096 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0540. Min Act: -0.0000

Data Index: 327518 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0564. Min Act: -0.0000

Data Index: 569241 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0509. Min Act: 0.0000

Data Index: 296533 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0531. Min Act: -0.0000

Data Index: 938810 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1414424 (Python Code)

Max Activating Token Index: 225

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0531. Min Act: -0.0000

Data Index: 135179 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0492. Min Act: -0.0000

Data Index: 135024 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0471. Min Act: -0.0000

Data Index: 976276 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0474. Min Act: -0.0000

Data Index: 1180902 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0490. Min Act: 0.0000

Data Index: 202296 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0475. Min Act: 0.0002

Data Index: 426269 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0493. Min Act: -0.0000

Data Index: 597206 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0475. Min Act: 0.0000

Data Index: 614032 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0469. Min Act: 0.0000

Data Index: 472026 (C4 (Web Text))

Max Activating Token Index: 891