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

Dataset: The Pile

Neuron 5032 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: 0.3109. Min Range: -0.3109

Max Act: 0.3083. Min Act: -0.0000

Data Index: 1651510 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.3109. Min Act: -0.0000

Data Index: 1923720 (The Pile)

Max Activating Token Index: 771

Text #2

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1936791 (The Pile)

Max Activating Token Index: 75

Text #3

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2975. Min Act: -0.0000

Data Index: 404786 (The Pile)

Max Activating Token Index: 384

Text #4

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2286. Min Act: -0.0000

Data Index: 135827 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1619268 (The Pile)

Max Activating Token Index: 125

Text #6

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1372768 (The Pile)

Max Activating Token Index: 795

Text #7

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2394. Min Act: -0.0000

Data Index: 846040 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1411755 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2587. Min Act: -0.0000

Data Index: 1754420 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2520. Min Act: -0.0000

Data Index: 990579 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1000833 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1340372 (The Pile)

Max Activating Token Index: 327

Text #13

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1783935 (The Pile)

Max Activating Token Index: 507

Text #14

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1014943 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2236. Min Act: -0.0000

Data Index: 246750 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2441. Min Act: -0.0000

Data Index: 1329696 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2694. Min Act: -0.0000

Data Index: 1652937 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1644838 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 0.3109. Min Range: -0.3109

Max Act: 0.2364. Min Act: -0.0000

Data Index: 458991 (The Pile)

Max Activating Token Index: 692