Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 502 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.5163. Min Act: -0.0001

Data Index: 967191 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4436. Min Act: -0.0001

Data Index: 384846 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4858. Min Act: -0.0001

Data Index: 662288 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4825. Min Act: -0.0001

Data Index: 602205 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4307. Min Act: -0.0001

Data Index: 200908 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3701. Min Act: -0.0001

Data Index: 611368 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4419. Min Act: -0.0001

Data Index: 651982 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4127. Min Act: -0.0001

Data Index: 533491 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3936. Min Act: -0.0001

Data Index: 395716 (C4 (Web Text))

Max Activating Token Index: 392

Text #9

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3961. Min Act: -0.0001

Data Index: 491734 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3966. Min Act: -0.0001

Data Index: 106537 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3664. Min Act: -0.0001

Data Index: 85072 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4129. Min Act: -0.0001

Data Index: 297401 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3488. Min Act: -0.0001

Data Index: 569373 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4271. Min Act: -0.0001

Data Index: 859979 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3744. Min Act: -0.0001

Data Index: 803531 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3762. Min Act: -0.0001

Data Index: 724994 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3778. Min Act: -0.0001

Data Index: 1071200 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3353. Min Act: -0.0001

Data Index: 596992 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3871. Min Act: -0.0001

Data Index: 101545 (C4 (Web Text))

Max Activating Token Index: 426