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

Dataset: The Pile

Neuron 2637 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: 1.2377. Min Range: -1.2377

Max Act: 1.2032. Min Act: -0.0000

Data Index: 525584 (The Pile)

Max Activating Token Index: 520

Text #1

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1376521 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.1276. Min Act: -0.0000

Data Index: 46619 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.2377. Min Act: -0.0000

Data Index: 601990 (The Pile)

Max Activating Token Index: 813

Text #4

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0343. Min Act: -0.0000

Data Index: 194821 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1668541 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1227660 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0347. Min Act: -0.0000

Data Index: 368644 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 1.2377. Min Range: -1.2377

Max Act: 1.0480. Min Act: -0.0000

Data Index: 165123 (The Pile)

Max Activating Token Index: 373

Text #9

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1284853 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1780552 (The Pile)

Max Activating Token Index: 684

Text #11

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9412. Min Act: -0.0000

Data Index: 294264 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1283412 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1787967 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1516036 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9114. Min Act: -0.0000

Data Index: 572257 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9120. Min Act: -0.0000

Data Index: 495317 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9686. Min Act: -0.0000

Data Index: 771022 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1806504 (The Pile)

Max Activating Token Index: 306

Text #19

Max Range: 1.2377. Min Range: -1.2377

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1074944 (The Pile)

Max Activating Token Index: 150