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

Dataset: The Pile

Neuron 4912 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1914647 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1115099 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3054. Min Act: -0.0000

Data Index: 702061 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3194. Min Act: -0.0000

Data Index: 385367 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1830821 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2792. Min Act: -0.0000

Data Index: 683604 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1589837 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1356582 (The Pile)

Max Activating Token Index: 27

Text #8

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1288438 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2761. Min Act: -0.0000

Data Index: 1129727 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1558703 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1140413 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1642380 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2573. Min Act: -0.0000

Data Index: 308585 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1418866 (The Pile)

Max Activating Token Index: 738

Text #15

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2549. Min Act: -0.0000

Data Index: 280436 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2374. Min Act: -0.0000

Data Index: 1095089 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1488791 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2518. Min Act: -0.0000

Data Index: 10937 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.2330. Min Act: -0.0000

Data Index: 160700 (The Pile)

Max Activating Token Index: 108