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

Dataset: The Pile

Neuron 564 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: 1.0816. Min Range: -1.0816

Max Act: 1.0816. Min Act: -0.0000

Data Index: 673092 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1497601 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1988128 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8866. Min Act: -0.0000

Data Index: 883608 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7572. Min Act: -0.0000

Data Index: 298448 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8492. Min Act: -0.0000

Data Index: 1846702 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8430. Min Act: -0.0000

Data Index: 443781 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1617682 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1409085 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7793. Min Act: -0.0000

Data Index: 56361 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7517. Min Act: -0.0000

Data Index: 217063 (The Pile)

Max Activating Token Index: 1009

Text #11

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1577592 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7573. Min Act: -0.0000

Data Index: 1426733 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1456510 (The Pile)

Max Activating Token Index: 557

Text #14

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7278. Min Act: -0.0000

Data Index: 388092 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1022476 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7335. Min Act: -0.0000

Data Index: 455984 (The Pile)

Max Activating Token Index: 838

Text #17

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1344411 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.6892. Min Act: -0.0000

Data Index: 974618 (The Pile)

Max Activating Token Index: 427

Text #19

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.6866. Min Act: -0.0000

Data Index: 953659 (The Pile)

Max Activating Token Index: 111