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

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

Neuron 1903 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0536. Min Act: -0.0005

Data Index: 1490931 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0541. Min Act: -0.0005

Data Index: 582713 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0513. Min Act: -0.0004

Data Index: 52109 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0530. Min Act: -0.0005

Data Index: 1532817 (Python Code)

Max Activating Token Index: 47

Text #4

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0496. Min Act: -0.0005

Data Index: 64718 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0482. Min Act: -0.0005

Data Index: 440744 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0485. Min Act: -0.0005

Data Index: 583817 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0480. Min Act: -0.0005

Data Index: 886681 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0475. Min Act: -0.0005

Data Index: 1048345 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0502. Min Act: -0.0005

Data Index: 120465 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0485. Min Act: -0.0005

Data Index: 650385 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0463. Min Act: -0.0005

Data Index: 861582 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0460. Min Act: -0.0005

Data Index: 670333 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0477. Min Act: -0.0005

Data Index: 1377255 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0437. Min Act: -0.0005

Data Index: 1250839 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0458. Min Act: -0.0005

Data Index: 227242 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0454. Min Act: -0.0005

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0462. Min Act: -0.0005

Data Index: 1299301 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0443. Min Act: -0.0005

Data Index: 1159565 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0541. Min Range: -0.0541

Max Act: 0.0461. Min Act: -0.0005

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 571