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

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

Neuron 2568 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.5798. Min Act: -0.0000

Data Index: 613504 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.5588. Min Act: -0.0000

Data Index: 1172102 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4561. Min Act: -0.0000

Data Index: 1246675 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.4475. Min Act: -0.0000

Data Index: 483938 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.2114. Min Act: -0.0000

Data Index: 978144 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3285. Min Act: -0.0000

Data Index: 72275 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.3148. Min Act: -0.0000

Data Index: 666855 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.1494. Min Act: -0.0000

Data Index: 197881 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.1483. Min Act: -0.0000

Data Index: 1024725 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 4.5798. Min Range: -4.5798

Max Act: 3.9472. Min Act: -0.0000

Data Index: 309365 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.0880. Min Act: -0.0000

Data Index: 684451 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.0827. Min Act: -0.0000

Data Index: 770249 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 4.5798. Min Range: -4.5798

Max Act: 3.9151. Min Act: -0.0000

Data Index: 1151005 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.0631. Min Act: -0.0000

Data Index: 79203 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.0609. Min Act: -0.0000

Data Index: 520911 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.2192. Min Act: -0.0000

Data Index: 726406 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 4.5798. Min Range: -4.5798

Max Act: 3.8647. Min Act: -0.0000

Data Index: 148550 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 4.5798. Min Range: -4.5798

Max Act: 4.0189. Min Act: -0.0000

Data Index: 1030253 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 4.5798. Min Range: -4.5798

Max Act: 3.8734. Min Act: -0.0000

Data Index: 444095 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 4.5798. Min Range: -4.5798

Max Act: 3.8603. Min Act: -0.0000

Data Index: 305268 (C4 (Web Text))

Max Activating Token Index: 839