Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5696 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0161. Min Range: -3.0161

Max Act: 3.0161. Min Act: -0.0000

Data Index: 363437 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 3.0161. Min Range: -3.0161

Max Act: 2.4117. Min Act: -0.0000

Data Index: 1029435 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 3.0161. Min Range: -3.0161

Max Act: 2.1186. Min Act: -0.0000

Data Index: 1065424 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 3.0161. Min Range: -3.0161

Max Act: 2.1618. Min Act: -0.0000

Data Index: 351813 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 3.0161. Min Range: -3.0161

Max Act: 2.3388. Min Act: -0.0000

Data Index: 315320 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 3.0161. Min Range: -3.0161

Max Act: 2.1868. Min Act: -0.0000

Data Index: 833229 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.6422. Min Act: -0.0000

Data Index: 36102 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.6896. Min Act: -0.0000

Data Index: 1149759 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.6284. Min Act: -0.0000

Data Index: 89718 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.6762. Min Act: -0.0000

Data Index: 986086 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.6306. Min Act: -0.0000

Data Index: 904765 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.6124. Min Act: -0.0000

Data Index: 617094 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.4985. Min Act: -0.0000

Data Index: 680712 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.5456. Min Act: -0.0000

Data Index: 713502 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.6202. Min Act: -0.0000

Data Index: 932228 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1086051 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.7155. Min Act: -0.0000

Data Index: 502677 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.4886. Min Act: -0.0000

Data Index: 701856 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.4061. Min Act: -0.0000

Data Index: 1081646 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 3.0161. Min Range: -3.0161

Max Act: 1.5798. Min Act: -0.0000

Data Index: 651625 (C4 (Web Text))

Max Activating Token Index: 107