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

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

Neuron 1420 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0006

Data Index: 305318 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0601. Min Act: -0.0006

Data Index: 62650 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0605. Min Act: -0.0006

Data Index: 110381 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0580. Min Act: -0.0006

Data Index: 199375 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0555. Min Act: -0.0006

Data Index: 1108159 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0529. Min Act: -0.0006

Data Index: 577498 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0518. Min Act: -0.0006

Data Index: 970509 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0527. Min Act: -0.0006

Data Index: 329468 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0511. Min Act: -0.0006

Data Index: 470211 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0517. Min Act: -0.0006

Data Index: 890128 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0496. Min Act: -0.0006

Data Index: 137576 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0480. Min Act: -0.0006

Data Index: 1030430 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0448. Min Act: -0.0006

Data Index: 563061 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0457. Min Act: -0.0006

Data Index: 209275 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0477. Min Act: -0.0006

Data Index: 918286 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0486. Min Act: -0.0006

Data Index: 791 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0490. Min Act: -0.0006

Data Index: 477786 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0482. Min Act: -0.0006

Data Index: 766756 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0470. Min Act: -0.0006

Data Index: 456969 (C4 (Web Text))

Max Activating Token Index: 606

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0467. Min Act: -0.0006

Data Index: 693004 (C4 (Web Text))

Max Activating Token Index: 536