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

Dataset: The Pile

Neuron 1528 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0551. Min Act: -0.0000

Data Index: 784511 (The Pile)

Max Activating Token Index: 333

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1061436 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0444. Min Act: -0.0001

Data Index: 1002685 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0462. Min Act: -0.0000

Data Index: 909260 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0473. Min Act: -0.0000

Data Index: 493844 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0459. Min Act: -0.0000

Data Index: 195507 (The Pile)

Max Activating Token Index: 491

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0460. Min Act: -0.0000

Data Index: 567603 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0465. Min Act: -0.0000

Data Index: 1423583 (The Pile)

Max Activating Token Index: 770

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0478. Min Act: -0.0000

Data Index: 1605092 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0443. Min Act: -0.0000

Data Index: 1114435 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0450. Min Act: -0.0000

Data Index: 868950 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1675880 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0468. Min Act: -0.0000

Data Index: 923249 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0457. Min Act: -0.0000

Data Index: 450404 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0443. Min Act: -0.0000

Data Index: 65674 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1383664 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0460. Min Act: -0.0000

Data Index: 310223 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0402. Min Act: -0.0000

Data Index: 103904 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0425. Min Act: -0.0000

Data Index: 254665 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0430. Min Act: -0.0000

Data Index: 242965 (The Pile)

Max Activating Token Index: 654