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

Dataset: The Pile

Neuron 2765 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1551883 (The Pile)

Max Activating Token Index: 493

Text #1

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4754. Min Act: -0.0000

Data Index: 632753 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1471784 (The Pile)

Max Activating Token Index: 883

Text #3

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1390922 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4791. Min Act: -0.0000

Data Index: 425727 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1118760 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.3892. Min Act: -0.0000

Data Index: 905977 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4480. Min Act: -0.0000

Data Index: 801494 (The Pile)

Max Activating Token Index: 399

Text #8

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4655. Min Act: -0.0000

Data Index: 105747 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1787177 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4656. Min Act: -0.0000

Data Index: 906245 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1093742 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4128. Min Act: -0.0000

Data Index: 459292 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4402. Min Act: -0.0000

Data Index: 806942 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1752138 (The Pile)

Max Activating Token Index: 77

Text #15

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1646501 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4308. Min Act: -0.0000

Data Index: 844620 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4131. Min Act: -0.0000

Data Index: 44766 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1934511 (The Pile)

Max Activating Token Index: 151

Text #19

Max Range: 0.6226. Min Range: -0.6226

Max Act: 0.3873. Min Act: -0.0000

Data Index: 792155 (The Pile)

Max Activating Token Index: 641