Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3924 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.6679. Min Range: -4.6679

Max Act: 4.6679. Min Act: -0.0000

Data Index: 1260709 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 4.6679. Min Range: -4.6679

Max Act: 3.6856. Min Act: -0.0000

Data Index: 853750 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 4.6679. Min Range: -4.6679

Max Act: 3.6750. Min Act: -0.0000

Data Index: 87 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 4.6679. Min Range: -4.6679

Max Act: 3.3556. Min Act: -0.0000

Data Index: 384493 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 4.6679. Min Range: -4.6679

Max Act: 3.2491. Min Act: -0.0000

Data Index: 1114146 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.9031. Min Act: -0.0000

Data Index: 625476 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 4.6679. Min Range: -4.6679

Max Act: 3.0070. Min Act: -0.0000

Data Index: 507099 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.4870. Min Act: -0.0000

Data Index: 1099928 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.6995. Min Act: -0.0000

Data Index: 638079 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.5522. Min Act: -0.0000

Data Index: 1000438 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.5523. Min Act: -0.0000

Data Index: 234439 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.8139. Min Act: -0.0000

Data Index: 1158150 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.6553. Min Act: -0.0000

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.5881. Min Act: -0.0000

Data Index: 1173453 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.5859. Min Act: -0.0000

Data Index: 234463 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.5676. Min Act: -0.0000

Data Index: 350791 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.6591. Min Act: -0.0000

Data Index: 97840 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.4771. Min Act: -0.0000

Data Index: 526029 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.3852. Min Act: -0.0000

Data Index: 911449 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 4.6679. Min Range: -4.6679

Max Act: 2.3381. Min Act: -0.0000

Data Index: 228601 (C4 (Web Text))

Max Activating Token Index: 882