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

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

Neuron 3679 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: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0001

Data Index: 1122409 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0641. Min Act: -0.0001

Data Index: 1338042 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0592. Min Act: -0.0001

Data Index: 274104 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0553. Min Act: -0.0001

Data Index: 881279 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0626. Min Act: -0.0001

Data Index: 711830 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0545. Min Act: -0.0001

Data Index: 6168 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0543. Min Act: -0.0001

Data Index: 278217 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0492. Min Act: -0.0001

Data Index: 436794 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0547. Min Act: -0.0001

Data Index: 768772 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1233940 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0599. Min Act: -0.0001

Data Index: 722737 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0507. Min Act: -0.0001

Data Index: 964023 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0520. Min Act: -0.0001

Data Index: 798614 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0461. Min Act: -0.0001

Data Index: 989230 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0568. Min Act: -0.0001

Data Index: 973526 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0523. Min Act: -0.0001

Data Index: 532577 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0443. Min Act: -0.0001

Data Index: 340761 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0460. Min Act: -0.0001

Data Index: 1631482 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0518. Min Act: -0.0001

Data Index: 1222138 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0527. Min Act: -0.0002

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 379