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

Dataset: The Pile

Neuron 3804 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6691. Min Range: -5.6691

Max Act: 5.5505. Min Act: -0.0000

Data Index: 479652 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 5.6691. Min Range: -5.6691

Max Act: 5.1843. Min Act: -0.0000

Data Index: 1723560 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 5.6691. Min Range: -5.6691

Max Act: 5.6691. Min Act: -0.0000

Data Index: 757369 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.6338. Min Act: -0.0000

Data Index: 864224 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.2682. Min Act: -0.0000

Data Index: 90880 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.4916. Min Act: -0.0000

Data Index: 290717 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 5.6691. Min Range: -5.6691

Max Act: 3.9826. Min Act: -0.0000

Data Index: 1273501 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.4161. Min Act: -0.0000

Data Index: 1713099 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.1914. Min Act: -0.0000

Data Index: 1448027 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.4576. Min Act: -0.0000

Data Index: 1162256 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.1109. Min Act: -0.0000

Data Index: 321155 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 5.6691. Min Range: -5.6691

Max Act: 3.9819. Min Act: -0.0000

Data Index: 563985 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.3361. Min Act: -0.0000

Data Index: 1150913 (The Pile)

Max Activating Token Index: 348

Text #13

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.2685. Min Act: -0.0000

Data Index: 1242833 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 5.6691. Min Range: -5.6691

Max Act: 3.5983. Min Act: -0.0000

Data Index: 1303634 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.2431. Min Act: -0.0000

Data Index: 138658 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 5.6691. Min Range: -5.6691

Max Act: 4.0920. Min Act: -0.0000

Data Index: 604369 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 5.6691. Min Range: -5.6691

Max Act: 3.8179. Min Act: -0.0000

Data Index: 1689775 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 5.6691. Min Range: -5.6691

Max Act: 3.9391. Min Act: -0.0000

Data Index: 158969 (The Pile)

Max Activating Token Index: 989

Text #19

Max Range: 5.6691. Min Range: -5.6691

Max Act: 3.7498. Min Act: -0.0000

Data Index: 327536 (The Pile)

Max Activating Token Index: 421