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

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

Neuron 2993 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0003

Data Index: 355330 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0464. Min Act: -0.0002

Data Index: 858810 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0441. Min Act: -0.0002

Data Index: 627331 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1325489 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0438. Min Act: -0.0003

Data Index: 631658 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0443. Min Act: -0.0003

Data Index: 67884 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0434. Min Act: -0.0003

Data Index: 919133 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0417. Min Act: -0.0002

Data Index: 387226 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0421. Min Act: -0.0002

Data Index: 868536 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1344569 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0407. Min Act: -0.0002

Data Index: 459620 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1190972 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0418. Min Act: -0.0002

Data Index: 52288 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0414. Min Act: -0.0002

Data Index: 883081 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0403. Min Act: -0.0002

Data Index: 750185 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0408. Min Act: -0.0003

Data Index: 714026 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0403. Min Act: -0.0003

Data Index: 23204 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1023159 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0396. Min Act: -0.0003

Data Index: 509039 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0387. Min Act: -0.0002

Data Index: 243081 (C4 (Web Text))

Max Activating Token Index: 104