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

Dataset: The Pile

Neuron 1507 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6907. Min Act: -0.0000

Data Index: 604414 (The Pile)

Max Activating Token Index: 949

Text #1

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.7198. Min Act: -0.0000

Data Index: 535595 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1738538 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1250702 (The Pile)

Max Activating Token Index: 972

Text #4

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1512865 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1472474 (The Pile)

Max Activating Token Index: 468

Text #6

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1584434 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1444438 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6043. Min Act: -0.0000

Data Index: 901807 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6503. Min Act: -0.0000

Data Index: 192935 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1434981 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1387753 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5999. Min Act: -0.0000

Data Index: 778579 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1862832 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5609. Min Act: -0.0000

Data Index: 407935 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1857689 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5872. Min Act: -0.0000

Data Index: 54872 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5474. Min Act: -0.0000

Data Index: 357253 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5472. Min Act: -0.0000

Data Index: 972864 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 0.7198. Min Range: -0.7198

Max Act: 0.5780. Min Act: -0.0000

Data Index: 549163 (The Pile)

Max Activating Token Index: 649