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

Dataset: The Pile

Neuron 1195 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.2503. Min Act: -0.0000

Data Index: 1294187 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.2542. Min Act: -0.0000

Data Index: 702962 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.1780. Min Act: -0.0000

Data Index: 331728 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1639609 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0781. Min Act: -0.0000

Data Index: 1652939 (The Pile)

Max Activating Token Index: 530

Text #5

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0120. Min Act: -0.0000

Data Index: 175532 (The Pile)

Max Activating Token Index: 986

Text #6

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0688. Min Act: -0.0000

Data Index: 898579 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1342774 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1322451 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0780. Min Act: -0.0000

Data Index: 513429 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0809. Min Act: -0.0000

Data Index: 445729 (The Pile)

Max Activating Token Index: 793

Text #11

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1680654 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0835. Min Act: -0.0000

Data Index: 643315 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.9464. Min Act: -0.0000

Data Index: 1463117 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.1996. Min Act: -0.0000

Data Index: 1531857 (The Pile)

Max Activating Token Index: 876

Text #15

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0008. Min Act: -0.0000

Data Index: 474878 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 1.2542. Min Range: -1.2542

Max Act: 1.0953. Min Act: -0.0000

Data Index: 1822368 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1586013 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.9749. Min Act: -0.0000

Data Index: 415964 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 1.2542. Min Range: -1.2542

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1701989 (The Pile)

Max Activating Token Index: 389