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

Dataset: The Pile

Neuron 4241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.7992. Min Act: -0.0000

Data Index: 1716539 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6519. Min Act: -0.0000

Data Index: 604577 (The Pile)

Max Activating Token Index: 576

Text #2

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1801077 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6083. Min Act: -0.0000

Data Index: 656023 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6343. Min Act: -0.0000

Data Index: 692818 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6266. Min Act: -0.0000

Data Index: 586177 (The Pile)

Max Activating Token Index: 531

Text #6

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6105. Min Act: -0.0000

Data Index: 632338 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6301. Min Act: -0.0000

Data Index: 435668 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5782. Min Act: -0.0000

Data Index: 1520960 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1270909 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1631866 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1701669 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5465. Min Act: -0.0000

Data Index: 177097 (The Pile)

Max Activating Token Index: 389

Text #13

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5808. Min Act: -0.0000

Data Index: 497865 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5730. Min Act: -0.0000

Data Index: 347176 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5624. Min Act: -0.0000

Data Index: 264172 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5493. Min Act: -0.0000

Data Index: 442598 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1923871 (The Pile)

Max Activating Token Index: 633

Text #18

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1955830 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1722024 (The Pile)

Max Activating Token Index: 98