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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1851 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.8169. Min Act: -0.0000

Data Index: 996483 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.1365. Min Act: -0.0000

Data Index: 1235229 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.9796. Min Act: -0.0000

Data Index: 39063 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.1344. Min Act: -0.0000

Data Index: 183448 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.2109. Min Act: -0.0000

Data Index: 699979 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.9731. Min Act: -0.0000

Data Index: 220337 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.9222. Min Act: -0.0000

Data Index: 931444 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.0360. Min Act: -0.0000

Data Index: 991289 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 3.8169. Min Range: -3.8169

Max Act: 3.0206. Min Act: -0.0000

Data Index: 1271082 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.7037. Min Act: -0.0000

Data Index: 1199604 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.8148. Min Act: -0.0000

Data Index: 1296449 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.6441. Min Act: -0.0000

Data Index: 53721 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.7759. Min Act: -0.0000

Data Index: 489864 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.7528. Min Act: -0.0000

Data Index: 826527 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.7382. Min Act: -0.0000

Data Index: 1148193 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.8708. Min Act: -0.0000

Data Index: 348484 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.7176. Min Act: -0.0000

Data Index: 1039530 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.5830. Min Act: -0.0000

Data Index: 1186120 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.5499. Min Act: -0.0000

Data Index: 854335 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 3.8169. Min Range: -3.8169

Max Act: 2.6902. Min Act: -0.0000

Data Index: 618951 (C4 (Web Text))

Max Activating Token Index: 540