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

Dataset: The Pile

Neuron 4497 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: 1.2641. Min Range: -1.2641

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1209283 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1466139 (The Pile)

Max Activating Token Index: 319

Text #2

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1594018 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2641. Min Act: -0.0000

Data Index: 776883 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1916768 (The Pile)

Max Activating Token Index: 156

Text #5

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0861. Min Act: -0.0001

Data Index: 1280916 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.2572. Min Act: -0.0000

Data Index: 1584899 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1146. Min Act: -0.0000

Data Index: 750540 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1604. Min Act: -0.0000

Data Index: 702235 (The Pile)

Max Activating Token Index: 243

Text #9

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1349257 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1990162 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1209. Min Act: -0.0000

Data Index: 525879 (The Pile)

Max Activating Token Index: 856

Text #12

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1190. Min Act: -0.0001

Data Index: 1818146 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1316. Min Act: -0.0000

Data Index: 360622 (The Pile)

Max Activating Token Index: 106

Text #14

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1883531 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1856822 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.1046. Min Act: -0.0000

Data Index: 756791 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0352. Min Act: -0.0000

Data Index: 503196 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1118471 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.2641. Min Range: -1.2641

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1352633 (The Pile)

Max Activating Token Index: 275