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

Dataset: The Pile

Neuron 1719 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0056. Min Range: -1.0056

Max Act: 1.0056. Min Act: -0.0000

Data Index: 286895 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7926. Min Act: -0.0000

Data Index: 289662 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7880. Min Act: -0.0000

Data Index: 37604 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7578. Min Act: -0.0000

Data Index: 866472 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1073402 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7289. Min Act: -0.0000

Data Index: 242922 (The Pile)

Max Activating Token Index: 344

Text #6

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1741018 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1768529 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1929992 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6545. Min Act: -0.0000

Data Index: 561343 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.7471. Min Act: -0.0000

Data Index: 358655 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1364711 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6717. Min Act: -0.0000

Data Index: 81175 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1427189 (The Pile)

Max Activating Token Index: 425

Text #14

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6640. Min Act: -0.0000

Data Index: 20373 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1280721 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1500654 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6607. Min Act: -0.0000

Data Index: 1038583 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1500478 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 1.0056. Min Range: -1.0056

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1706391 (The Pile)

Max Activating Token Index: 246