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

Dataset: The Pile

Neuron 884 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.8888. Min Act: -0.0000

Data Index: 824236 (The Pile)

Max Activating Token Index: 784

Text #1

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6239. Min Act: -0.0000

Data Index: 773909 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7889. Min Act: -0.0000

Data Index: 840428 (The Pile)

Max Activating Token Index: 173

Text #3

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1318331 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1242808 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7452. Min Act: -0.0000

Data Index: 341504 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1635190 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5889. Min Act: -0.0000

Data Index: 216411 (The Pile)

Max Activating Token Index: 337

Text #8

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1510154 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6487. Min Act: -0.0000

Data Index: 71122 (The Pile)

Max Activating Token Index: 829

Text #10

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6405. Min Act: -0.0000

Data Index: 783460 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6383. Min Act: -0.0000

Data Index: 1967125 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6397. Min Act: -0.0000

Data Index: 436394 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6348. Min Act: -0.0000

Data Index: 97047 (The Pile)

Max Activating Token Index: 947

Text #14

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6031. Min Act: -0.0000

Data Index: 784107 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6241. Min Act: -0.0000

Data Index: 978026 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6578. Min Act: -0.0000

Data Index: 909055 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6021. Min Act: -0.0000

Data Index: 837895 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5990. Min Act: -0.0000

Data Index: 493564 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5744. Min Act: -0.0000

Data Index: 466488 (The Pile)

Max Activating Token Index: 822