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

Dataset: The Pile

Neuron 3744 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: 0.8389. Min Range: -0.8389

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1418617 (The Pile)

Max Activating Token Index: 348

Text #1

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1878294 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7109. Min Act: -0.0000

Data Index: 482987 (The Pile)

Max Activating Token Index: 236

Text #3

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6923. Min Act: -0.0000

Data Index: 99119 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.6540. Min Act: -0.0000

Data Index: 44298 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1945583 (The Pile)

Max Activating Token Index: 381

Text #6

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5285. Min Act: -0.0000

Data Index: 188511 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1967464 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5072. Min Act: -0.0000

Data Index: 450925 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1072982 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5524. Min Act: -0.0000

Data Index: 808196 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1566671 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1565601 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1808571 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4532. Min Act: -0.0000

Data Index: 138037 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5284. Min Act: -0.0000

Data Index: 10755 (The Pile)

Max Activating Token Index: 328

Text #16

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1935085 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1887122 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4466. Min Act: -0.0000

Data Index: 861099 (The Pile)

Max Activating Token Index: 10

Text #19

Max Range: 0.8389. Min Range: -0.8389

Max Act: 0.4801. Min Act: -0.0000

Data Index: 94733 (The Pile)

Max Activating Token Index: 425