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

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

Neuron 3281 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.6254. Min Act: -0.0000

Data Index: 621705 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.5101. Min Act: -0.0000

Data Index: 800696 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3822. Min Act: -0.0000

Data Index: 610734 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3030. Min Act: -0.0000

Data Index: 105367 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3485. Min Act: -0.0000

Data Index: 389275 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1251705 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3046. Min Act: -0.0000

Data Index: 1245615 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2864. Min Act: -0.0000

Data Index: 468172 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1174240 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3015. Min Act: -0.0000

Data Index: 6734 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2292. Min Act: -0.0000

Data Index: 704312 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.3150. Min Act: -0.0000

Data Index: 889956 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2851. Min Act: -0.0000

Data Index: 449881 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1470692 (Python Code)

Max Activating Token Index: 638

Text #14

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.2093. Min Act: -0.0000

Data Index: 716060 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1487. Min Act: -0.0000

Data Index: 532380 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1127. Min Act: -0.0000

Data Index: 125497 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1017093 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1571. Min Act: -0.0000

Data Index: 648988 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 1.6254. Min Range: -1.6254

Max Act: 1.1702. Min Act: -0.0000

Data Index: 829676 (C4 (Web Text))

Max Activating Token Index: 818