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

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

Neuron 1457 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.8214. Min Act: -0.0002

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.7425. Min Act: -0.0002

Data Index: 908665 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.7625. Min Act: -0.0002

Data Index: 1349724 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5103. Min Act: -0.0002

Data Index: 1171727 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5095. Min Act: -0.0002

Data Index: 1196739 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5448. Min Act: -0.0003

Data Index: 731089 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4987. Min Act: -0.0002

Data Index: 1110302 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.5198. Min Act: -0.0002

Data Index: 443854 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4470. Min Act: -0.0002

Data Index: 1127495 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4946. Min Act: -0.0002

Data Index: 732251 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4590. Min Act: -0.0002

Data Index: 197666 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4758. Min Act: -0.0002

Data Index: 1182603 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4602. Min Act: -0.0002

Data Index: 53624 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4905. Min Act: -0.0002

Data Index: 913317 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4473. Min Act: -0.0002

Data Index: 988494 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4451. Min Act: -0.0002

Data Index: 746815 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4718. Min Act: -0.0002

Data Index: 1324430 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4364. Min Act: -0.0002

Data Index: 1182925 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4520. Min Act: -0.0002

Data Index: 369397 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.8214. Min Range: -0.8214

Max Act: 0.4851. Min Act: -0.0002

Data Index: 1025796 (C4 (Web Text))

Max Activating Token Index: 350