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

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

Neuron 1143 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.6201. Min Act: -0.0000

Data Index: 485145 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.2068. Min Act: -0.0000

Data Index: 295002 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.0761. Min Act: -0.0000

Data Index: 258075 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1329022 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.0116. Min Act: -0.0000

Data Index: 721255 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.9869. Min Act: -0.0000

Data Index: 1356374 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.6201. Min Range: -1.6201

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1314586 (C4 (Web Text))

Max Activating Token Index: 360

Text #7

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.9569. Min Act: -0.0000

Data Index: 976593 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1123600 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1242809 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.8885. Min Act: -0.0000

Data Index: 492274 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.8650. Min Act: -0.0000

Data Index: 102345 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.8250. Min Act: -0.0000

Data Index: 802868 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.7714. Min Act: -0.0000

Data Index: 370843 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.8403. Min Act: -0.0000

Data Index: 818125 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.7877. Min Act: -0.0000

Data Index: 652224 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.7755. Min Act: -0.0000

Data Index: 609052 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.8092. Min Act: -0.0000

Data Index: 631916 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.7917. Min Act: -0.0000

Data Index: 300168 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 1.6201. Min Range: -1.6201

Max Act: 0.7479. Min Act: -0.0000

Data Index: 848448 (C4 (Web Text))

Max Activating Token Index: 69