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

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

Neuron 2793 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0624. Min Act: -0.0001

Data Index: 453451 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1400036 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0538. Min Act: -0.0001

Data Index: 75221 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0519. Min Act: -0.0001

Data Index: 289119 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0542. Min Act: -0.0001

Data Index: 64584 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0471. Min Act: -0.0002

Data Index: 355943 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0458. Min Act: -0.0001

Data Index: 18078 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0487. Min Act: -0.0001

Data Index: 468021 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1395409 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0434. Min Act: -0.0001

Data Index: 98358 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0463. Min Act: -0.0001

Data Index: 381631 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1012855 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0466. Min Act: -0.0001

Data Index: 790425 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0454. Min Act: -0.0002

Data Index: 333785 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0430. Min Act: -0.0002

Data Index: 741444 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1544998 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1607907 (Python Code)

Max Activating Token Index: 808

Text #17

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1478094 (Python Code)

Max Activating Token Index: 165

Text #18

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0424. Min Act: -0.0001

Data Index: 31583 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0435. Min Act: -0.0001

Data Index: 1073792 (C4 (Web Text))

Max Activating Token Index: 532