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

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

Neuron 1033 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1347. Min Act: -0.0002

Data Index: 283011 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1358. Min Act: -0.0002

Data Index: 392607 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1259. Min Act: -0.0002

Data Index: 984226 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1080866 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1223. Min Act: -0.0002

Data Index: 843138 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1321129 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1119. Min Act: -0.0002

Data Index: 63936 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1077. Min Act: -0.0002

Data Index: 628516 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1094. Min Act: -0.0002

Data Index: 970353 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1320541 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1066. Min Act: -0.0002

Data Index: 167115 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1107. Min Act: -0.0002

Data Index: 695488 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1099. Min Act: -0.0002

Data Index: 777120 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1103. Min Act: -0.0002

Data Index: 539272 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1087. Min Act: -0.0002

Data Index: 873810 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1019. Min Act: -0.0002

Data Index: 789161 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1046. Min Act: -0.0002

Data Index: 785441 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1090362 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1040. Min Act: -0.0002

Data Index: 32904 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1358. Min Range: -0.1358

Max Act: 0.1028. Min Act: -0.0002

Data Index: 650624 (C4 (Web Text))

Max Activating Token Index: 581