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

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

Neuron 539 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1341791 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1144. Min Act: -0.0001

Data Index: 27496 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1344. Min Act: -0.0001

Data Index: 779262 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1257808 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1211. Min Act: -0.0001

Data Index: 533666 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1209. Min Act: -0.0001

Data Index: 779277 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1235. Min Act: -0.0001

Data Index: 449475 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1180. Min Act: -0.0001

Data Index: 967408 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1065975 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1114. Min Act: -0.0001

Data Index: 69234 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1125. Min Act: -0.0001

Data Index: 239271 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1115. Min Act: -0.0001

Data Index: 829699 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1329336 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1115. Min Act: -0.0001

Data Index: 242608 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1021. Min Act: -0.0001

Data Index: 550464 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1053. Min Act: -0.0001

Data Index: 741333 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1013. Min Act: -0.0001

Data Index: 113238 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1038. Min Act: -0.0001

Data Index: 79608 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1037. Min Act: -0.0001

Data Index: 245880 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1023. Min Act: -0.0001

Data Index: 539973 (C4 (Web Text))

Max Activating Token Index: 834