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

Dataset: The Pile

Neuron 2500 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: 0.9446. Min Range: -0.9446

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1704360 (The Pile)

Max Activating Token Index: 10

Text #1

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8941. Min Act: -0.0000

Data Index: 376292 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1603699 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8920. Min Act: -0.0000

Data Index: 1488605 (The Pile)

Max Activating Token Index: 247

Text #4

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8568. Min Act: -0.0000

Data Index: 777171 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7907. Min Act: -0.0000

Data Index: 274159 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8236. Min Act: -0.0000

Data Index: 424579 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1764289 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8633. Min Act: -0.0000

Data Index: 147467 (The Pile)

Max Activating Token Index: 755

Text #9

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8209. Min Act: -0.0000

Data Index: 1846784 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8354. Min Act: -0.0000

Data Index: 154276 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8796. Min Act: -0.0000

Data Index: 271603 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1598644 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1162593 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7840. Min Act: -0.0000

Data Index: 922550 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1945941 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6802. Min Act: -0.0000

Data Index: 773626 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6943. Min Act: -0.0000

Data Index: 798452 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1678677 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 0.9446. Min Range: -0.9446

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1843519 (The Pile)

Max Activating Token Index: 593