Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5680 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.7929. Min Act: -0.0000

Data Index: 721488 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.8235. Min Act: -0.0000

Data Index: 1038470 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.5143. Min Act: -0.0000

Data Index: 884371 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.6404. Min Act: -0.0000

Data Index: 459274 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.7702. Min Act: -0.0000

Data Index: 775959 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.5038. Min Act: -0.0000

Data Index: 143659 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.6620. Min Act: -0.0000

Data Index: 485754 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.3528. Min Act: -0.0000

Data Index: 1062898 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.4758. Min Act: -0.0000

Data Index: 54789 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.5823. Min Act: -0.0000

Data Index: 1142745 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.4270. Min Act: -0.0000

Data Index: 1267380 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.2338. Min Act: -0.0000

Data Index: 531446 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.2089. Min Act: 0.0000

Data Index: 1121468 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.3060. Min Act: -0.0000

Data Index: 1138272 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.2954. Min Act: -0.0000

Data Index: 1233250 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.2575. Min Act: -0.0000

Data Index: 1235422 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.3708. Min Act: -0.0000

Data Index: 524417 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.2214. Min Act: -0.0000

Data Index: 42586 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.1661. Min Act: -0.0000

Data Index: 501200 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 2.8235. Min Range: -2.8235

Max Act: 2.1400. Min Act: -0.0000

Data Index: 1155535 (C4 (Web Text))

Max Activating Token Index: 383