Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1368 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0641. Min Act: -0.0002

Data Index: 234763 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0596. Min Act: -0.0002

Data Index: 341441 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0601. Min Act: -0.0002

Data Index: 438034 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0590. Min Act: -0.0001

Data Index: 926163 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0566. Min Act: -0.0002

Data Index: 433460 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0567. Min Act: -0.0002

Data Index: 144665 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0552. Min Act: -0.0002

Data Index: 86523 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0535. Min Act: -0.0002

Data Index: 400434 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0554. Min Act: -0.0002

Data Index: 890342 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0567. Min Act: -0.0002

Data Index: 986911 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0555. Min Act: -0.0002

Data Index: 999345 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1337989 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0573. Min Act: -0.0002

Data Index: 445056 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1175830 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0516. Min Act: -0.0002

Data Index: 484878 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0529. Min Act: -0.0001

Data Index: 97152 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0552. Min Act: -0.0002

Data Index: 271304 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0525. Min Act: -0.0002

Data Index: 899135 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0568. Min Act: -0.0002

Data Index: 609400 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0641. Min Range: -0.0641

Max Act: 0.0507. Min Act: -0.0002

Data Index: 441255 (C4 (Web Text))

Max Activating Token Index: 863