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

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

Neuron 1097 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: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0005

Data Index: 998529 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0535. Min Act: -0.0005

Data Index: 237660 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0514. Min Act: -0.0005

Data Index: 328618 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0497. Min Act: -0.0005

Data Index: 906856 (C4 (Web Text))

Max Activating Token Index: 742

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0486. Min Act: -0.0005

Data Index: 186565 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0505. Min Act: -0.0005

Data Index: 508182 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0500. Min Act: -0.0005

Data Index: 499888 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0503. Min Act: -0.0005

Data Index: 676235 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0479. Min Act: -0.0005

Data Index: 855456 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0497. Min Act: -0.0005

Data Index: 429707 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0468. Min Act: -0.0005

Data Index: 494649 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0472. Min Act: -0.0005

Data Index: 859874 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0466. Min Act: -0.0005

Data Index: 987567 (C4 (Web Text))

Max Activating Token Index: 936

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0468. Min Act: -0.0005

Data Index: 941588 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0469. Min Act: -0.0005

Data Index: 1328641 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0465. Min Act: -0.0005

Data Index: 1281026 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0463. Min Act: -0.0005

Data Index: 434863 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0466. Min Act: -0.0005

Data Index: 495402 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0453. Min Act: -0.0005

Data Index: 1358627 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0464. Min Act: -0.0005

Data Index: 851908 (C4 (Web Text))

Max Activating Token Index: 355