Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1757 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3891. Min Act: -0.0000

Data Index: 434532 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3831. Min Act: -0.0000

Data Index: 345293 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.3616. Min Act: -0.0000

Data Index: 136871 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2963. Min Act: -0.0000

Data Index: 335545 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2787. Min Act: -0.0000

Data Index: 164291 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2870. Min Act: -0.0000

Data Index: 786363 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2748. Min Act: -0.0000

Data Index: 99690 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2576. Min Act: -0.0000

Data Index: 43627 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2680. Min Act: -0.0000

Data Index: 532033 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1070618 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2501. Min Act: -0.0000

Data Index: 206709 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2574. Min Act: -0.0000

Data Index: 1053554 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1155543 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2544. Min Act: -0.0000

Data Index: 986280 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2341. Min Act: -0.0000

Data Index: 314960 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1104191 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1237729 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2374. Min Act: -0.0000

Data Index: 396346 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2445. Min Act: -0.0000

Data Index: 394922 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.3891. Min Range: -0.3891

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1231566 (C4 (Web Text))

Max Activating Token Index: 738