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

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

Neuron 1996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1226. Min Act: -0.0000

Data Index: 332994 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1261. Min Act: -0.0000

Data Index: 1297202 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1175. Min Act: -0.0000

Data Index: 663262 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1143. Min Act: 0.0001

Data Index: 955629 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1179. Min Act: -0.0000

Data Index: 605541 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1136. Min Act: -0.0000

Data Index: 314589 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1082174 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1081. Min Act: -0.0001

Data Index: 500113 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1282352 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1003. Min Act: -0.0000

Data Index: 552412 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1230289 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1012. Min Act: -0.0000

Data Index: 72705 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1119913 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1022. Min Act: -0.0000

Data Index: 855793 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0991. Min Act: -0.0000

Data Index: 187527 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0978. Min Act: -0.0000

Data Index: 207730 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0942. Min Act: -0.0001

Data Index: 143970 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0948. Min Act: -0.0000

Data Index: 281425 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0987. Min Act: -0.0000

Data Index: 174543 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0988. Min Act: -0.0000

Data Index: 483107 (C4 (Web Text))

Max Activating Token Index: 523