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

Dataset: The Pile

Neuron 4950 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: 0.3552. Min Range: -0.3552

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1322587 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3552. Min Act: -0.0000

Data Index: 154262 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3060. Min Act: -0.0000

Data Index: 1929876 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3197. Min Act: -0.0000

Data Index: 668395 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1047887 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1376802 (The Pile)

Max Activating Token Index: 989

Text #6

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2905. Min Act: -0.0000

Data Index: 512846 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1999153 (The Pile)

Max Activating Token Index: 58

Text #8

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2753. Min Act: -0.0000

Data Index: 412917 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2824. Min Act: -0.0000

Data Index: 1698389 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2922. Min Act: -0.0000

Data Index: 923504 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1626571 (The Pile)

Max Activating Token Index: 976

Text #12

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2855. Min Act: -0.0000

Data Index: 726210 (The Pile)

Max Activating Token Index: 1005

Text #13

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1081974 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2219. Min Act: -0.0000

Data Index: 806632 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2691. Min Act: -0.0000

Data Index: 587065 (The Pile)

Max Activating Token Index: 743

Text #16

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2669. Min Act: -0.0000

Data Index: 533561 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1646055 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2513. Min Act: -0.0000

Data Index: 897725 (The Pile)

Max Activating Token Index: 196

Text #19

Max Range: 0.3552. Min Range: -0.3552

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1333528 (The Pile)

Max Activating Token Index: 725