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

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

Neuron 3998 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.7497. Min Act: -0.0002

Data Index: 1144844 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.7116. Min Act: -0.0002

Data Index: 895475 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6771. Min Act: -0.0003

Data Index: 173104 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6624. Min Act: -0.0003

Data Index: 1321143 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6670. Min Act: -0.0002

Data Index: 982827 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6217. Min Act: -0.0003

Data Index: 840273 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6337. Min Act: -0.0003

Data Index: 735630 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6324. Min Act: -0.0003

Data Index: 366914 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6263. Min Act: -0.0003

Data Index: 645472 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6026. Min Act: -0.0003

Data Index: 489530 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5948. Min Act: -0.0003

Data Index: 67752 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.6118. Min Act: -0.0003

Data Index: 252397 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5956. Min Act: -0.0003

Data Index: 729832 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5865. Min Act: -0.0003

Data Index: 385583 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5852. Min Act: -0.0002

Data Index: 1062140 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5456. Min Act: -0.0003

Data Index: 1150167 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5508. Min Act: -0.0003

Data Index: 513538 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5459. Min Act: -0.0003

Data Index: 657333 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5683. Min Act: -0.0002

Data Index: 1234457 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.7497. Min Range: -0.7497

Max Act: 0.5299. Min Act: -0.0003

Data Index: 1045676 (C4 (Web Text))

Max Activating Token Index: 557