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

Dataset: The Pile

Neuron 3369 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: 1.9030. Min Range: -1.9030

Max Act: 1.8343. Min Act: -0.0000

Data Index: 80176 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7272. Min Act: -0.0000

Data Index: 822132 (The Pile)

Max Activating Token Index: 946

Text #2

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.9030. Min Act: -0.0000

Data Index: 1009289 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7969. Min Act: -0.0000

Data Index: 751923 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.8808. Min Act: -0.0000

Data Index: 1417995 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.8207. Min Act: -0.0000

Data Index: 1649600 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1817052 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7053. Min Act: -0.0000

Data Index: 1610212 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.8269. Min Act: -0.0000

Data Index: 1194588 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7801. Min Act: -0.0000

Data Index: 837526 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7729. Min Act: -0.0000

Data Index: 873639 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.6738. Min Act: -0.0000

Data Index: 896754 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.8163. Min Act: -0.0000

Data Index: 1614972 (The Pile)

Max Activating Token Index: 54

Text #13

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.6727. Min Act: -0.0000

Data Index: 1312477 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7430. Min Act: -0.0000

Data Index: 1373534 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7485. Min Act: -0.0000

Data Index: 1517745 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.6936. Min Act: -0.0000

Data Index: 584709 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7295. Min Act: -0.0000

Data Index: 1328174 (The Pile)

Max Activating Token Index: 342

Text #18

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7264. Min Act: -0.0000

Data Index: 1617216 (The Pile)

Max Activating Token Index: 76

Text #19

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.6830. Min Act: -0.0000

Data Index: 1310747 (The Pile)

Max Activating Token Index: 155