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

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

Neuron 2375 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1391. Min Range: -1.1391

Max Act: 1.1306. Min Act: -0.0001

Data Index: 85754 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 1.1391. Min Range: -1.1391

Max Act: 1.1391. Min Act: -0.0001

Data Index: 981679 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1098030 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.1391. Min Range: -1.1391

Max Act: 1.0040. Min Act: -0.0001

Data Index: 409247 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.9705. Min Act: -0.0001

Data Index: 304912 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.9424. Min Act: -0.0001

Data Index: 210681 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8165. Min Act: -0.0001

Data Index: 212114 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8921. Min Act: -0.0001

Data Index: 306280 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8245. Min Act: -0.0001

Data Index: 768028 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.9264. Min Act: -0.0001

Data Index: 41766 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7019. Min Act: -0.0001

Data Index: 198852 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8326. Min Act: -0.0001

Data Index: 1151365 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8046. Min Act: -0.0001

Data Index: 926844 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7495. Min Act: -0.0001

Data Index: 181145 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7943. Min Act: -0.0001

Data Index: 1355059 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8157. Min Act: -0.0001

Data Index: 386285 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8280. Min Act: -0.0001

Data Index: 739302 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8239. Min Act: -0.0001

Data Index: 1144923 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7985. Min Act: -0.0001

Data Index: 874183 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7959. Min Act: -0.0001

Data Index: 596636 (C4 (Web Text))

Max Activating Token Index: 956