Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1107 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1781. Min Act: -0.0001

Data Index: 418759 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0631. Min Act: -0.0001

Data Index: 1231492 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8978. Min Act: -0.0001

Data Index: 1217959 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8194. Min Act: -0.0001

Data Index: 354634 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1017381 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8920. Min Act: -0.0001

Data Index: 510968 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8220. Min Act: -0.0000

Data Index: 760168 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8727. Min Act: -0.0001

Data Index: 1226138 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1040201 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8371. Min Act: -0.0001

Data Index: 722768 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.7899. Min Act: -0.0001

Data Index: 488344 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8049. Min Act: -0.0000

Data Index: 859090 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.7022. Min Act: -0.0001

Data Index: 800144 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.6831. Min Act: -0.0000

Data Index: 336024 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.6766. Min Act: -0.0001

Data Index: 833805 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.7859. Min Act: -0.0001

Data Index: 1218399 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1212683 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1326455 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.6641. Min Act: -0.0000

Data Index: 298884 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.7404. Min Act: -0.0000

Data Index: 113194 (C4 (Web Text))

Max Activating Token Index: 472