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

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

Neuron 17 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1157. Min Range: -1.1157

Max Act: 1.1157. Min Act: -0.0001

Data Index: 714778 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.9170. Min Act: -0.0001

Data Index: 881467 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8735. Min Act: -0.0001

Data Index: 340849 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8937. Min Act: -0.0001

Data Index: 336521 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.8286. Min Act: -0.0001

Data Index: 385423 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7825. Min Act: -0.0001

Data Index: 529764 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7602. Min Act: -0.0001

Data Index: 476786 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7809. Min Act: -0.0001

Data Index: 258816 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.6985. Min Act: -0.0001

Data Index: 559762 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.6765. Min Act: -0.0001

Data Index: 298464 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.6256. Min Act: -0.0001

Data Index: 1051017 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7344. Min Act: -0.0001

Data Index: 15237 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7098. Min Act: -0.0001

Data Index: 643124 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.6755. Min Act: -0.0001

Data Index: 593256 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7343. Min Act: -0.0001

Data Index: 1241531 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7656. Min Act: -0.0001

Data Index: 962703 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7185. Min Act: -0.0001

Data Index: 251230 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.6429. Min Act: -0.0001

Data Index: 650151 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7630. Min Act: -0.0001

Data Index: 548126 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.1157. Min Range: -1.1157

Max Act: 0.7003. Min Act: -0.0001

Data Index: 361844 (C4 (Web Text))

Max Activating Token Index: 669