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

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

Neuron 5196 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6646. Min Range: -4.6646

Max Act: 4.6646. Min Act: -0.0000

Data Index: 796006 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 4.6646. Min Range: -4.6646

Max Act: 3.4841. Min Act: -0.0000

Data Index: 1077858 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 4.6646. Min Range: -4.6646

Max Act: 3.4775. Min Act: -0.0000

Data Index: 1023024 (C4 (Web Text))

Max Activating Token Index: 488

Text #3

Max Range: 4.6646. Min Range: -4.6646

Max Act: 3.4017. Min Act: -0.0000

Data Index: 933660 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 4.6646. Min Range: -4.6646

Max Act: 3.3842. Min Act: -0.0000

Data Index: 157876 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 4.6646. Min Range: -4.6646

Max Act: 3.2413. Min Act: -0.0000

Data Index: 102975 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.9264. Min Act: -0.0000

Data Index: 523228 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.9867. Min Act: -0.0000

Data Index: 488599 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.9612. Min Act: -0.0000

Data Index: 415946 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 4.6646. Min Range: -4.6646

Max Act: 3.2127. Min Act: -0.0000

Data Index: 37363 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.9978. Min Act: -0.0000

Data Index: 578972 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 4.6646. Min Range: -4.6646

Max Act: 3.2348. Min Act: -0.0000

Data Index: 129381 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.9034. Min Act: -0.0000

Data Index: 626572 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.7494. Min Act: -0.0000

Data Index: 370857 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.8711. Min Act: -0.0000

Data Index: 1144856 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.7186. Min Act: -0.0000

Data Index: 497853 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.8502. Min Act: -0.0000

Data Index: 456993 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 4.6646. Min Range: -4.6646

Max Act: 3.0943. Min Act: -0.0000

Data Index: 1313435 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.5356. Min Act: -0.0000

Data Index: 25086 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 4.6646. Min Range: -4.6646

Max Act: 2.6386. Min Act: -0.0000

Data Index: 1156025 (C4 (Web Text))

Max Activating Token Index: 446