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

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

Neuron 2926 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1121. Min Act: -0.0001

Data Index: 482481 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1133113 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1029. Min Act: -0.0001

Data Index: 354114 (C4 (Web Text))

Max Activating Token Index: 294

Text #3

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.1127. Min Act: -0.0001

Data Index: 808407 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0972. Min Act: -0.0001

Data Index: 572208 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0994. Min Act: -0.0001

Data Index: 309122 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0964. Min Act: -0.0001

Data Index: 873738 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1336616 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0902. Min Act: -0.0001

Data Index: 454430 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0988. Min Act: -0.0000

Data Index: 745974 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0997. Min Act: -0.0001

Data Index: 717935 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0931. Min Act: -0.0001

Data Index: 500890 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0929. Min Act: -0.0001

Data Index: 3782 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0919. Min Act: -0.0001

Data Index: 495147 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1044952 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0915. Min Act: -0.0001

Data Index: 296268 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0941. Min Act: -0.0000

Data Index: 278452 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1024807 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0912. Min Act: -0.0001

Data Index: 757132 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.1127. Min Range: -0.1127

Max Act: 0.0879. Min Act: -0.0000

Data Index: 477546 (C4 (Web Text))

Max Activating Token Index: 247