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

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

Neuron 1543 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1149895 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4994. Min Act: -0.0000

Data Index: 870441 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4374. Min Act: -0.0000

Data Index: 599695 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4033. Min Act: -0.0000

Data Index: 535863 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4409. Min Act: -0.0000

Data Index: 472441 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4194. Min Act: -0.0000

Data Index: 152506 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4353. Min Act: -0.0000

Data Index: 394244 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4279. Min Act: -0.0000

Data Index: 678740 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1001576 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3967. Min Act: -0.0000

Data Index: 540567 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4250. Min Act: -0.0000

Data Index: 408846 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3491. Min Act: -0.0000

Data Index: 872729 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3827. Min Act: -0.0000

Data Index: 765167 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.4193. Min Act: -0.0000

Data Index: 381325 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3571. Min Act: -0.0000

Data Index: 147217 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3031. Min Act: -0.0000

Data Index: 54757 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1213212 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3774. Min Act: -0.0000

Data Index: 317044 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3640. Min Act: -0.0000

Data Index: 491416 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.5175. Min Range: -0.5175

Max Act: 0.3404. Min Act: -0.0000

Data Index: 475366 (C4 (Web Text))

Max Activating Token Index: 277