Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 384 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0006

Data Index: 956333 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0302. Min Act: -0.0006

Data Index: 462569 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1038987 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0294. Min Act: -0.0006

Data Index: 142546 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0299. Min Act: -0.0006

Data Index: 692264 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0296. Min Act: -0.0006

Data Index: 669968 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1192591 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0287. Min Act: -0.0006

Data Index: 883840 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1320933 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0284. Min Act: -0.0006

Data Index: 338055 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0284. Min Act: -0.0006

Data Index: 614943 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0281. Min Act: -0.0006

Data Index: 221833 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0287. Min Act: -0.0006

Data Index: 555512 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0285. Min Act: -0.0006

Data Index: 1300132 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0265. Min Act: -0.0006

Data Index: 449051 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0282. Min Act: -0.0006

Data Index: 908129 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0265. Min Act: -0.0006

Data Index: 90825 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0275. Min Act: -0.0006

Data Index: 1188901 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0286. Min Act: -0.0006

Data Index: 867712 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0267. Min Act: -0.0006

Data Index: 181372 (C4 (Web Text))

Max Activating Token Index: 546