Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 685 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0407. Min Act: -0.0000

Data Index: 1360554 (The Pile)

Max Activating Token Index: 645

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0405. Min Act: -0.0000

Data Index: 474505 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0402. Min Act: -0.0000

Data Index: 557700 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0402. Min Act: -0.0000

Data Index: 170485 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1038327 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1607026 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0000

Data Index: 141625 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0394. Min Act: -0.0000

Data Index: 1131505 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1682954 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1961537 (The Pile)

Max Activating Token Index: 508

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0389. Min Act: -0.0000

Data Index: 460470 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0387. Min Act: -0.0000

Data Index: 327835 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1437110 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0372. Min Act: 0.0000

Data Index: 1531843 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0368. Min Act: -0.0000

Data Index: 1051708 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0382. Min Act: -0.0000

Data Index: 1653326 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1952152 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0379. Min Act: -0.0001

Data Index: 927051 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0376. Min Act: -0.0000

Data Index: 852649 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1334921 (The Pile)

Max Activating Token Index: 692