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

Dataset: The Pile

Neuron 1519 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: 0.3612. Min Range: -0.3612

Max Act: 0.3611. Min Act: -0.0000

Data Index: 640648 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3612. Min Act: -0.0000

Data Index: 896010 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3513. Min Act: -0.0000

Data Index: 268130 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3289. Min Act: -0.0000

Data Index: 75565 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1571699 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1791772 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3185. Min Act: -0.0000

Data Index: 321995 (The Pile)

Max Activating Token Index: 903

Text #7

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1333717 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1210472 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3008. Min Act: -0.0000

Data Index: 787247 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1446467 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3124. Min Act: -0.0000

Data Index: 353635 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1937195 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1919162 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1111483 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2904. Min Act: -0.0000

Data Index: 180971 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1142196 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2836. Min Act: -0.0000

Data Index: 1655418 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.2952. Min Act: -0.0000

Data Index: 655882 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.3612. Min Range: -0.3612

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1345963 (The Pile)

Max Activating Token Index: 741