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

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

Neuron 2980 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: 0.2917. Min Range: -0.2917

Max Act: 0.2917. Min Act: -0.0001

Data Index: 614456 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2425. Min Act: -0.0001

Data Index: 191155 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2425. Min Act: -0.0001

Data Index: 236709 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2335. Min Act: -0.0001

Data Index: 517523 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2332. Min Act: -0.0001

Data Index: 833633 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2144. Min Act: -0.0001

Data Index: 1356946 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1043508 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2118. Min Act: -0.0001

Data Index: 998141 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2112. Min Act: -0.0001

Data Index: 1058325 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1841. Min Act: -0.0001

Data Index: 955390 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2021. Min Act: -0.0001

Data Index: 622598 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2099. Min Act: -0.0001

Data Index: 1202910 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1930. Min Act: -0.0001

Data Index: 629993 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2102. Min Act: -0.0001

Data Index: 664131 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1846. Min Act: -0.0001

Data Index: 690336 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2028. Min Act: -0.0001

Data Index: 430320 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1748. Min Act: -0.0001

Data Index: 367464 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2343. Min Act: -0.0001

Data Index: 804162 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2093. Min Act: -0.0001

Data Index: 851588 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1327237 (C4 (Web Text))

Max Activating Token Index: 86