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

Dataset: The Pile

Neuron 1598 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: 4.1493. Min Range: -4.1493

Max Act: 4.1493. Min Act: -0.0000

Data Index: 1221896 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.6643. Min Act: -0.0000

Data Index: 1754171 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.4430. Min Act: -0.0000

Data Index: 1867601 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.8548. Min Act: -0.0000

Data Index: 1221690 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.5154. Min Act: -0.0000

Data Index: 1913405 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.4834. Min Act: -0.0000

Data Index: 1238901 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.4464. Min Act: -0.0000

Data Index: 528655 (The Pile)

Max Activating Token Index: 109

Text #7

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.1648. Min Act: -0.0000

Data Index: 1367950 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.5543. Min Act: -0.0000

Data Index: 52256 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.4800. Min Act: -0.0000

Data Index: 782167 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.0469. Min Act: -0.0000

Data Index: 1672496 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.2832. Min Act: -0.0000

Data Index: 982891 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.2580. Min Act: -0.0000

Data Index: 423184 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.1237. Min Act: -0.0000

Data Index: 106711 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.3665. Min Act: -0.0000

Data Index: 544972 (The Pile)

Max Activating Token Index: 644

Text #15

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.3885. Min Act: -0.0000

Data Index: 340286 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.4857. Min Act: -0.0000

Data Index: 1860346 (The Pile)

Max Activating Token Index: 288

Text #17

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.2319. Min Act: -0.0000

Data Index: 78674 (The Pile)

Max Activating Token Index: 570

Text #18

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.1652. Min Act: -0.0000

Data Index: 456121 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 4.1493. Min Range: -4.1493

Max Act: 3.1722. Min Act: -0.0000

Data Index: 1146216 (The Pile)

Max Activating Token Index: 455