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

Dataset: The Pile

Neuron 1182 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: 1.5157. Min Range: -1.5157

Max Act: 1.5157. Min Act: -0.0000

Data Index: 1586016 (The Pile)

Max Activating Token Index: 473

Text #1

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.3512. Min Act: -0.0000

Data Index: 148331 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.4162. Min Act: -0.0000

Data Index: 1997572 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.3352. Min Act: -0.0000

Data Index: 415883 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.2021. Min Act: -0.0000

Data Index: 828391 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.3355. Min Act: -0.0000

Data Index: 955683 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1392215 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.2451. Min Act: -0.0000

Data Index: 475163 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.2541. Min Act: -0.0000

Data Index: 1224944 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.1698. Min Act: -0.0000

Data Index: 245191 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1716139 (The Pile)

Max Activating Token Index: 223

Text #11

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1690091 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.0858. Min Act: -0.0000

Data Index: 504098 (The Pile)

Max Activating Token Index: 726

Text #13

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.0437. Min Act: -0.0000

Data Index: 495813 (The Pile)

Max Activating Token Index: 18

Text #14

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.0348. Min Act: -0.0000

Data Index: 434000 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.0580. Min Act: -0.0000

Data Index: 1013851 (The Pile)

Max Activating Token Index: 153

Text #16

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1229960 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.0403. Min Act: -0.0000

Data Index: 1307879 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 1.5157. Min Range: -1.5157

Max Act: 0.9716. Min Act: -0.0000

Data Index: 914976 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 1.5157. Min Range: -1.5157

Max Act: 1.0497. Min Act: -0.0000

Data Index: 976646 (The Pile)

Max Activating Token Index: 740