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

Dataset: The Pile

Neuron 2916 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.7325. Min Act: -0.0000

Data Index: 622851 (The Pile)

Max Activating Token Index: 330

Text #1

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.7975. Min Act: -0.0000

Data Index: 1344907 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.6897. Min Act: -0.0000

Data Index: 1269258 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.6156. Min Act: -0.0000

Data Index: 630282 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1486093 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1562130 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2948. Min Act: -0.0000

Data Index: 1258302 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3222. Min Act: -0.0000

Data Index: 133771 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0893. Min Act: -0.0000

Data Index: 464293 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0771. Min Act: -0.0000

Data Index: 77332 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1451. Min Act: -0.0000

Data Index: 1293180 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1608. Min Act: -0.0000

Data Index: 1978082 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1315482 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1331638 (The Pile)

Max Activating Token Index: 878

Text #14

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0281. Min Act: -0.0000

Data Index: 946531 (The Pile)

Max Activating Token Index: 885

Text #15

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0040. Min Act: -0.0000

Data Index: 144271 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0504. Min Act: -0.0000

Data Index: 240579 (The Pile)

Max Activating Token Index: 862

Text #17

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0085. Min Act: -0.0000

Data Index: 1820236 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 1.7975. Min Range: -1.7975

Max Act: 0.9532. Min Act: -0.0000

Data Index: 1322222 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1853663 (The Pile)

Max Activating Token Index: 923