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

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

Neuron 5784 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4497. Min Range: -1.4497

Max Act: 1.4497. Min Act: -0.0000

Data Index: 255112 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 1.4497. Min Range: -1.4497

Max Act: 1.3833. Min Act: -0.0000

Data Index: 664911 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.4497. Min Range: -1.4497

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1018606 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 1.4497. Min Range: -1.4497

Max Act: 1.3897. Min Act: -0.0000

Data Index: 339187 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.4497. Min Range: -1.4497

Max Act: 1.3812. Min Act: -0.0000

Data Index: 44611 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1101103 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1216522 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.6573. Min Act: -0.0000

Data Index: 719406 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.6493. Min Act: -0.0000

Data Index: 1122656 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.5915. Min Act: -0.0000

Data Index: 838175 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1104103 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.5728. Min Act: -0.0000

Data Index: 381548 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.5425. Min Act: -0.0000

Data Index: 848330 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.5672. Min Act: -0.0000

Data Index: 809662 (C4 (Web Text))

Max Activating Token Index: 905

Text #14

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1175787 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.5066. Min Act: -0.0000

Data Index: 343741 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.5488. Min Act: -0.0000

Data Index: 338568 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.4911. Min Act: -0.0000

Data Index: 820406 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.4813. Min Act: -0.0000

Data Index: 294011 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.4497. Min Range: -1.4497

Max Act: 0.4103. Min Act: -0.0000

Data Index: 701031 (C4 (Web Text))

Max Activating Token Index: 349