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

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

Neuron 4724 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3321. Min Act: -0.0000

Data Index: 493071 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3090. Min Act: -0.0000

Data Index: 255564 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3041. Min Act: -0.0000

Data Index: 195757 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2962. Min Act: -0.0000

Data Index: 404211 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2993. Min Act: -0.0000

Data Index: 616512 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2786. Min Act: -0.0000

Data Index: 294689 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2863. Min Act: -0.0000

Data Index: 847399 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2811. Min Act: -0.0000

Data Index: 558663 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2893. Min Act: -0.0000

Data Index: 861216 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2850. Min Act: -0.0000

Data Index: 52618 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2707. Min Act: -0.0000

Data Index: 266077 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2603. Min Act: -0.0000

Data Index: 45228 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2608. Min Act: -0.0000

Data Index: 324564 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1009076 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1250920 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2733. Min Act: -0.0000

Data Index: 47337 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2626. Min Act: -0.0000

Data Index: 952396 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2680. Min Act: -0.0000

Data Index: 537573 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2689. Min Act: -0.0000

Data Index: 160017 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2558. Min Act: -0.0000

Data Index: 165585 (C4 (Web Text))

Max Activating Token Index: 742