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

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

Neuron 1114 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3573. Min Act: -0.0000

Data Index: 36426 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1493375 (Python Code)

Max Activating Token Index: 799

Text #2

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3154. Min Act: -0.0000

Data Index: 1487039 (Python Code)

Max Activating Token Index: 352

Text #3

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1485671 (Python Code)

Max Activating Token Index: 423

Text #4

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3059. Min Act: -0.0000

Data Index: 89958 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1407838 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2846. Min Act: -0.0000

Data Index: 130499 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1353823 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1106376 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1224426 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1548872 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1166362 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1634737 (Python Code)

Max Activating Token Index: 771

Text #13

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2818. Min Act: -0.0000

Data Index: 572411 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2763. Min Act: -0.0000

Data Index: 1247918 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2729. Min Act: -0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2645. Min Act: -0.0000

Data Index: 1573554 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1255704 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1395629 (Python Code)

Max Activating Token Index: 350

Text #19

Max Range: 0.3573. Min Range: -0.3573

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1220558 (C4 (Web Text))

Max Activating Token Index: 569