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

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

Neuron 1052 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.1349. Min Act: -0.0001

Data Index: 497385 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9714. Min Act: -0.0001

Data Index: 486281 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.2214. Min Act: -0.0001

Data Index: 306957 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0944. Min Act: -0.0001

Data Index: 142950 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.2214. Min Range: -1.2214

Max Act: 1.0005. Min Act: -0.0001

Data Index: 713549 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9334. Min Act: -0.0001

Data Index: 810739 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8838. Min Act: -0.0001

Data Index: 1099730 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9012. Min Act: -0.0001

Data Index: 837082 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.9492. Min Act: -0.0001

Data Index: 872067 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8870. Min Act: -0.0001

Data Index: 836902 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8455. Min Act: -0.0001

Data Index: 230061 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1230689 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8666. Min Act: -0.0001

Data Index: 610336 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8589. Min Act: -0.0001

Data Index: 1160642 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8090. Min Act: -0.0001

Data Index: 998221 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.7973. Min Act: -0.0001

Data Index: 95720 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.7745. Min Act: -0.0001

Data Index: 1110467 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8257. Min Act: -0.0001

Data Index: 375274 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.8406. Min Act: -0.0001

Data Index: 1269487 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.2214. Min Range: -1.2214

Max Act: 0.7141. Min Act: -0.0001

Data Index: 1086749 (C4 (Web Text))

Max Activating Token Index: 451