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

Dataset: The Pile

Neuron 5027 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: 0.4861. Min Range: -0.4861

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1017625 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4832. Min Act: -0.0000

Data Index: 347423 (The Pile)

Max Activating Token Index: 496

Text #2

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1118841 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4592. Min Act: -0.0000

Data Index: 950077 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1588408 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4340. Min Act: -0.0000

Data Index: 436825 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1130162 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1623665 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1716071 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4028. Min Act: -0.0000

Data Index: 110836 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3915. Min Act: -0.0000

Data Index: 778966 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4364. Min Act: -0.0000

Data Index: 83240 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1494908 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4034. Min Act: -0.0000

Data Index: 186552 (The Pile)

Max Activating Token Index: 700

Text #14

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4101. Min Act: -0.0000

Data Index: 858495 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1567921 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3807. Min Act: -0.0000

Data Index: 423241 (The Pile)

Max Activating Token Index: 10

Text #17

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4317. Min Act: -0.0000

Data Index: 304394 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1430311 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 0.4861. Min Range: -0.4861

Max Act: 0.3873. Min Act: -0.0000

Data Index: 710988 (The Pile)

Max Activating Token Index: 325