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

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

Neuron 3667 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.5087. Min Act: -0.0000

Data Index: 418038 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.2695. Min Act: -0.0000

Data Index: 73485 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.0342. Min Act: -0.0000

Data Index: 270038 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.8290. Min Act: -0.0000

Data Index: 978582 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.5087. Min Range: -1.5087

Max Act: 1.0776. Min Act: -0.0000

Data Index: 752195 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.8866. Min Act: -0.0000

Data Index: 487671 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1077927 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.6358. Min Act: -0.0000

Data Index: 222759 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.5910. Min Act: -0.0000

Data Index: 23462 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.5689. Min Act: -0.0000

Data Index: 693035 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.4568. Min Act: -0.0000

Data Index: 596427 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1239300 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.3572. Min Act: -0.0000

Data Index: 240217 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.3163. Min Act: -0.0000

Data Index: 187438 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1020983 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1420494 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1324266 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1489761 (Python Code)

Max Activating Token Index: 953

Text #18

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.2606. Min Act: -0.0000

Data Index: 328334 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 1.5087. Min Range: -1.5087

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1431857 (Python Code)

Max Activating Token Index: 498