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

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

Neuron 4027 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: 0.6535. Min Range: -0.6535

Max Act: 0.6535. Min Act: -0.0000

Data Index: 744939 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6115. Min Act: -0.0000

Data Index: 885636 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1285349 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.6022. Min Act: -0.0001

Data Index: 849387 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5998. Min Act: -0.0001

Data Index: 1068308 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5577. Min Act: -0.0000

Data Index: 510734 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5718. Min Act: -0.0000

Data Index: 1261365 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5690. Min Act: -0.0000

Data Index: 882049 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1092612 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1212641 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5473. Min Act: -0.0000

Data Index: 132385 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5255. Min Act: -0.0001

Data Index: 772685 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5202. Min Act: -0.0000

Data Index: 409803 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5332. Min Act: -0.0000

Data Index: 963883 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5337. Min Act: -0.0000

Data Index: 1231142 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5318. Min Act: -0.0001

Data Index: 799279 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1211816 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5387. Min Act: -0.0000

Data Index: 100629 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.5192. Min Act: -0.0000

Data Index: 506085 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.6535. Min Range: -0.6535

Max Act: 0.4949. Min Act: -0.0000

Data Index: 658616 (C4 (Web Text))

Max Activating Token Index: 943