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

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

Neuron 1047 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1135994 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4374. Min Act: -0.0000

Data Index: 719364 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4396. Min Act: -0.0000

Data Index: 922569 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4473. Min Act: -0.0000

Data Index: 14607 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4390. Min Act: -0.0000

Data Index: 278436 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1052991 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1298681 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4052. Min Act: -0.0000

Data Index: 873315 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4279. Min Act: -0.0000

Data Index: 115402 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1341602 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4170. Min Act: -0.0000

Data Index: 881406 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4303. Min Act: -0.0000

Data Index: 807457 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4160. Min Act: -0.0000

Data Index: 580945 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4166. Min Act: -0.0000

Data Index: 303803 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4154. Min Act: -0.0000

Data Index: 362742 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4258. Min Act: -0.0000

Data Index: 897032 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4147. Min Act: -0.0000

Data Index: 1031709 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4127. Min Act: -0.0000

Data Index: 764177 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.4112. Min Act: -0.0000

Data Index: 9706 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.4781. Min Range: -0.4781

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1155791 (C4 (Web Text))

Max Activating Token Index: 83