Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2818 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1815. Min Act: -0.0000

Data Index: 162939 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1995486 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1542. Min Act: -0.0000

Data Index: 76935 (The Pile)

Max Activating Token Index: 698

Text #3

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1335144 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1455. Min Act: -0.0000

Data Index: 478101 (The Pile)

Max Activating Token Index: 721

Text #5

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1628145 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1435. Min Act: -0.0000

Data Index: 1320371 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1367. Min Act: -0.0000

Data Index: 1089656 (The Pile)

Max Activating Token Index: 869

Text #8

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1990982 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1698507 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1379. Min Act: -0.0000

Data Index: 104293 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1429. Min Act: -0.0000

Data Index: 455810 (The Pile)

Max Activating Token Index: 696

Text #12

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1589584 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1308. Min Act: -0.0000

Data Index: 660446 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1508206 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1405. Min Act: -0.0000

Data Index: 692578 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1343. Min Act: -0.0000

Data Index: 463171 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1113466 (The Pile)

Max Activating Token Index: 29

Text #18

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1371. Min Act: -0.0000

Data Index: 322665 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 0.1815. Min Range: -0.1815

Max Act: 0.1268. Min Act: -0.0000

Data Index: 424987 (The Pile)

Max Activating Token Index: 318