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

Dataset: The Pile

Neuron 5046 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: 1.6884. Min Range: -1.6884

Max Act: 1.6884. Min Act: -0.0000

Data Index: 836116 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1429436 (The Pile)

Max Activating Token Index: 659

Text #2

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1505286 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3884. Min Act: -0.0000

Data Index: 898169 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2048. Min Act: -0.0000

Data Index: 192246 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3405. Min Act: -0.0000

Data Index: 674546 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1865. Min Act: -0.0000

Data Index: 88305 (The Pile)

Max Activating Token Index: 1013

Text #7

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1732617 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3090. Min Act: -0.0000

Data Index: 1238741 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1773199 (The Pile)

Max Activating Token Index: 724

Text #10

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1501. Min Act: -0.0000

Data Index: 650904 (The Pile)

Max Activating Token Index: 274

Text #11

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1167607 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1860. Min Act: -0.0000

Data Index: 1382859 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1840. Min Act: -0.0000

Data Index: 286097 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1807. Min Act: -0.0000

Data Index: 1259509 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1045806 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1234134 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1618464 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1303. Min Act: -0.0000

Data Index: 820100 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1248. Min Act: -0.0000

Data Index: 1555590 (The Pile)

Max Activating Token Index: 502