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

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

Neuron 572 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3974. Min Act: -0.0000

Data Index: 635831 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3047. Min Act: -0.0000

Data Index: 163604 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3220. Min Act: -0.0000

Data Index: 24700 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3086. Min Act: -0.0000

Data Index: 814651 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2792. Min Act: -0.0000

Data Index: 308481 (C4 (Web Text))

Max Activating Token Index: 560

Text #5

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3009. Min Act: -0.0000

Data Index: 98191 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3008. Min Act: -0.0000

Data Index: 723690 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2972. Min Act: -0.0000

Data Index: 718988 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.3052. Min Act: -0.0000

Data Index: 1348401 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2821. Min Act: 0.0000

Data Index: 200925 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2935. Min Act: -0.0000

Data Index: 500597 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2836. Min Act: -0.0000

Data Index: 603225 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2821. Min Act: -0.0000

Data Index: 569489 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2793. Min Act: -0.0000

Data Index: 830837 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1261292 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2559. Min Act: -0.0000

Data Index: 520692 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2496. Min Act: -0.0000

Data Index: 98208 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2431. Min Act: -0.0000

Data Index: 579276 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2605. Min Act: -0.0000

Data Index: 736790 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.3974. Min Range: -0.3974

Max Act: 0.2525. Min Act: -0.0000

Data Index: 949369 (C4 (Web Text))

Max Activating Token Index: 105