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

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

Neuron 1663 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.7010. Min Act: -0.0001

Data Index: 80815 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.6641. Min Act: -0.0001

Data Index: 1288100 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5718. Min Act: -0.0001

Data Index: 998194 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5932. Min Act: -0.0001

Data Index: 1304303 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5613. Min Act: -0.0001

Data Index: 1197997 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5314. Min Act: -0.0001

Data Index: 181235 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4976. Min Act: -0.0001

Data Index: 954487 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.5127. Min Act: -0.0001

Data Index: 1231644 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4874. Min Act: -0.0001

Data Index: 573767 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4851. Min Act: -0.0001

Data Index: 1334948 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4812. Min Act: -0.0001

Data Index: 803151 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4630. Min Act: -0.0001

Data Index: 1308131 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4891. Min Act: -0.0001

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4640. Min Act: -0.0001

Data Index: 734942 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4200. Min Act: -0.0001

Data Index: 50130 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4427. Min Act: -0.0001

Data Index: 1064430 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4065. Min Act: -0.0001

Data Index: 1203758 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4516. Min Act: -0.0001

Data Index: 1241917 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4373. Min Act: -0.0001

Data Index: 198096 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.7010. Min Range: -0.7010

Max Act: 0.4469. Min Act: -0.0001

Data Index: 720425 (C4 (Web Text))

Max Activating Token Index: 510