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

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

Neuron 560 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0001

Data Index: 358914 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0802. Min Act: -0.0001

Data Index: 588825 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0609. Min Act: -0.0001

Data Index: 254390 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0541. Min Act: -0.0001

Data Index: 727552 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0583. Min Act: -0.0001

Data Index: 815161 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1015827 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0566. Min Act: -0.0001

Data Index: 325439 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0544. Min Act: -0.0001

Data Index: 101861 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0540. Min Act: -0.0001

Data Index: 990829 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0498. Min Act: -0.0001

Data Index: 537163 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1284394 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0551. Min Act: -0.0001

Data Index: 634750 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0513. Min Act: -0.0001

Data Index: 54958 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0543. Min Act: -0.0001

Data Index: 605739 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0491. Min Act: -0.0001

Data Index: 478881 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0483. Min Act: -0.0001

Data Index: 217389 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0470. Min Act: -0.0001

Data Index: 205383 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1297332 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0482. Min Act: -0.0001

Data Index: 122896 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0454. Min Act: -0.0001

Data Index: 582310 (C4 (Web Text))

Max Activating Token Index: 37