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

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

Neuron 5038 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8312. Min Range: -4.8312

Max Act: 4.8312. Min Act: -0.0000

Data Index: 193723 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 4.8312. Min Range: -4.8312

Max Act: 4.6577. Min Act: -0.0000

Data Index: 418467 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 4.8312. Min Range: -4.8312

Max Act: 4.3856. Min Act: -0.0000

Data Index: 503171 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 4.8312. Min Range: -4.8312

Max Act: 4.3500. Min Act: -0.0000

Data Index: 239007 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.8162. Min Act: -0.0000

Data Index: 823213 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.7677. Min Act: -0.0000

Data Index: 563679 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.4119. Min Act: -0.0000

Data Index: 483789 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.3236. Min Act: -0.0000

Data Index: 609844 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.1824. Min Act: -0.0000

Data Index: 832856 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.4400. Min Act: -0.0000

Data Index: 795762 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.2468. Min Act: -0.0000

Data Index: 634493 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.1841. Min Act: -0.0000

Data Index: 945539 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.0292. Min Act: -0.0000

Data Index: 1194882 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.1499. Min Act: -0.0000

Data Index: 375219 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.2775. Min Act: -0.0000

Data Index: 536895 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.0817. Min Act: -0.0000

Data Index: 338802 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.0629. Min Act: -0.0000

Data Index: 1030454 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.0141. Min Act: -0.0000

Data Index: 60366 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 4.8312. Min Range: -4.8312

Max Act: 3.1519. Min Act: -0.0000

Data Index: 368015 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 4.8312. Min Range: -4.8312

Max Act: 2.8640. Min Act: -0.0000

Data Index: 948313 (C4 (Web Text))

Max Activating Token Index: 675