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

Dataset: The Pile

Neuron 4699 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.9350. Min Act: -0.0000

Data Index: 349990 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.8931. Min Act: -0.0000

Data Index: 1585925 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.9053. Min Act: -0.0000

Data Index: 1392678 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.7213. Min Act: -0.0000

Data Index: 1042703 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.5142. Min Act: -0.0000

Data Index: 1192144 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.4831. Min Act: -0.0000

Data Index: 1549311 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1970126 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.5065. Min Act: -0.0000

Data Index: 607079 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1170059 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.4825. Min Act: -0.0000

Data Index: 1789429 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.4752. Min Act: -0.0000

Data Index: 470850 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.4163. Min Act: -0.0000

Data Index: 601435 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.3989. Min Act: -0.0000

Data Index: 1671689 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1420101 (The Pile)

Max Activating Token Index: 323

Text #14

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1919495 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.3929. Min Act: -0.0000

Data Index: 1639718 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.4708. Min Act: -0.0000

Data Index: 274479 (The Pile)

Max Activating Token Index: 893

Text #17

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.3809. Min Act: -0.0000

Data Index: 974775 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.3824. Min Act: -0.0000

Data Index: 1625749 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 1.9350. Min Range: -1.9350

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1658098 (The Pile)

Max Activating Token Index: 485