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

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

Neuron 1545 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.8974. Min Act: -0.0000

Data Index: 1003116 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 2.0424. Min Range: -2.0424

Max Act: 2.0424. Min Act: -0.0000

Data Index: 1058585 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.7351. Min Act: -0.0000

Data Index: 652512 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.6216. Min Act: -0.0000

Data Index: 778326 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.4161. Min Act: -0.0000

Data Index: 622371 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.5740. Min Act: -0.0000

Data Index: 1261649 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.5901. Min Act: -0.0000

Data Index: 125561 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.4157. Min Act: -0.0000

Data Index: 167558 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.4264. Min Act: -0.0000

Data Index: 448215 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.4971. Min Act: -0.0000

Data Index: 669551 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.3890. Min Act: -0.0000

Data Index: 50660 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.3176. Min Act: -0.0000

Data Index: 444574 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.4337. Min Act: -0.0000

Data Index: 844763 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.4911. Min Act: -0.0000

Data Index: 987453 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.4008. Min Act: -0.0000

Data Index: 14139 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.1810. Min Act: -0.0000

Data Index: 571699 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.2246. Min Act: -0.0000

Data Index: 456102 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.3076. Min Act: -0.0000

Data Index: 878039 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.3496. Min Act: -0.0000

Data Index: 783143 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 2.0424. Min Range: -2.0424

Max Act: 1.2455. Min Act: -0.0000

Data Index: 779622 (C4 (Web Text))

Max Activating Token Index: 623