Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 765 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1084742 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0606. Min Act: -0.0003

Data Index: 443062 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0579. Min Act: -0.0003

Data Index: 902155 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0536. Min Act: -0.0003

Data Index: 555694 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0561. Min Act: -0.0003

Data Index: 317618 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0569. Min Act: -0.0003

Data Index: 287397 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0566. Min Act: -0.0003

Data Index: 546707 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0545. Min Act: -0.0003

Data Index: 851129 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1252955 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1485191 (Python Code)

Max Activating Token Index: 587

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0548. Min Act: -0.0004

Data Index: 1261583 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1019794 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0543. Min Act: -0.0004

Data Index: 1125544 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0544. Min Act: -0.0003

Data Index: 61497 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0533. Min Act: -0.0003

Data Index: 460498 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0534. Min Act: -0.0003

Data Index: 293323 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0530. Min Act: -0.0004

Data Index: 185040 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0515. Min Act: -0.0003

Data Index: 926981 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0517. Min Act: -0.0003

Data Index: 611497 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0505. Min Act: -0.0003

Data Index: 134586 (C4 (Web Text))

Max Activating Token Index: 580