Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 637 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1396420 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1621341 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.4670. Min Act: -0.0000

Data Index: 210819 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.3121. Min Act: -0.0000

Data Index: 991409 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1747292 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.3936. Min Act: -0.0000

Data Index: 315765 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.3026. Min Act: -0.0000

Data Index: 1471429 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2137. Min Act: -0.0000

Data Index: 516723 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2330. Min Act: -0.0000

Data Index: 726891 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2322. Min Act: -0.0000

Data Index: 1492547 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2432. Min Act: -0.0000

Data Index: 394540 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.3161. Min Act: -0.0000

Data Index: 658714 (The Pile)

Max Activating Token Index: 551

Text #12

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1105. Min Act: -0.0000

Data Index: 436866 (The Pile)

Max Activating Token Index: 725

Text #13

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2197. Min Act: -0.0000

Data Index: 1158631 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1662. Min Act: -0.0000

Data Index: 167134 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.2405. Min Act: -0.0000

Data Index: 525664 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1904. Min Act: -0.0000

Data Index: 680288 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1625831 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1368. Min Act: -0.0000

Data Index: 388247 (The Pile)

Max Activating Token Index: 683

Text #19

Max Range: 1.5335. Min Range: -1.5335

Max Act: 1.1729. Min Act: -0.0000

Data Index: 416623 (The Pile)

Max Activating Token Index: 491