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

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

Neuron 5741 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.2562. Min Act: -0.0000

Data Index: 360428 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 5.2562. Min Range: -5.2562

Max Act: 5.1221. Min Act: -0.0000

Data Index: 743237 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.6652. Min Act: -0.0000

Data Index: 606802 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.8068. Min Act: -0.0000

Data Index: 1009188 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.9329. Min Act: -0.0000

Data Index: 272723 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.9120. Min Act: -0.0000

Data Index: 39684 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.7155. Min Act: -0.0000

Data Index: 1143935 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.8512. Min Act: -0.0000

Data Index: 776655 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.6732. Min Act: -0.0000

Data Index: 776894 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.6628. Min Act: -0.0000

Data Index: 1214725 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.4904. Min Act: -0.0000

Data Index: 887551 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.5762. Min Act: -0.0000

Data Index: 652425 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.5498. Min Act: -0.0000

Data Index: 280368 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.5590. Min Act: -0.0000

Data Index: 1145499 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.5126. Min Act: -0.0000

Data Index: 125947 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.4650. Min Act: -0.0000

Data Index: 1003512 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.2785. Min Act: -0.0000

Data Index: 237329 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.4284. Min Act: -0.0000

Data Index: 1013009 (C4 (Web Text))

Max Activating Token Index: 274

Text #18

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.4136. Min Act: -0.0000

Data Index: 439961 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 5.2562. Min Range: -5.2562

Max Act: 4.2527. Min Act: -0.0000

Data Index: 631175 (C4 (Web Text))

Max Activating Token Index: 243