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

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

Neuron 4108 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3579. Min Range: -2.3579

Max Act: 2.2644. Min Act: -0.0000

Data Index: 455381 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 2.3579. Min Range: -2.3579

Max Act: 2.3579. Min Act: -0.0000

Data Index: 314905 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 2.3579. Min Range: -2.3579

Max Act: 2.1464. Min Act: -0.0000

Data Index: 1358847 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.9756. Min Act: -0.0000

Data Index: 288436 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.8659. Min Act: -0.0000

Data Index: 400439 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.8989. Min Act: -0.0000

Data Index: 378678 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 2.3579. Min Range: -2.3579

Max Act: 2.0121. Min Act: -0.0000

Data Index: 31318 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.9534. Min Act: -0.0000

Data Index: 1231701 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.7460. Min Act: -0.0000

Data Index: 899284 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.9002. Min Act: -0.0000

Data Index: 649822 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.7444. Min Act: -0.0000

Data Index: 727835 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 2.3579. Min Range: -2.3579

Max Act: 2.0010. Min Act: -0.0000

Data Index: 959672 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.6435. Min Act: -0.0000

Data Index: 697314 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.8177. Min Act: -0.0000

Data Index: 1106778 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.7196. Min Act: -0.0000

Data Index: 544522 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1081626 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.6066. Min Act: -0.0000

Data Index: 239402 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.8023. Min Act: -0.0000

Data Index: 500833 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.5731. Min Act: -0.0000

Data Index: 1321513 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 2.3579. Min Range: -2.3579

Max Act: 1.7200. Min Act: -0.0000

Data Index: 986339 (C4 (Web Text))

Max Activating Token Index: 812