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

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

Neuron 2646 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.6121. Min Range: -7.6121

Max Act: 7.6121. Min Act: -0.0001

Data Index: 1260747 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 7.6121. Min Range: -7.6121

Max Act: 6.9331. Min Act: -0.0000

Data Index: 1259091 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 7.6121. Min Range: -7.6121

Max Act: 6.2380. Min Act: -0.0000

Data Index: 1254019 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 7.6121. Min Range: -7.6121

Max Act: 5.6184. Min Act: -0.0000

Data Index: 1069231 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 7.6121. Min Range: -7.6121

Max Act: 5.3254. Min Act: -0.0000

Data Index: 670201 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 7.6121. Min Range: -7.6121

Max Act: 4.9981. Min Act: -0.0000

Data Index: 1255101 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 7.6121. Min Range: -7.6121

Max Act: 5.1267. Min Act: -0.0000

Data Index: 178331 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 7.6121. Min Range: -7.6121

Max Act: 4.7618. Min Act: -0.0000

Data Index: 198288 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 7.6121. Min Range: -7.6121

Max Act: 4.2858. Min Act: -0.0000

Data Index: 173007 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 7.6121. Min Range: -7.6121

Max Act: 4.6807. Min Act: -0.0000

Data Index: 437990 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 7.6121. Min Range: -7.6121

Max Act: 3.8181. Min Act: -0.0000

Data Index: 1115077 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 7.6121. Min Range: -7.6121

Max Act: 4.2580. Min Act: -0.0000

Data Index: 880436 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 7.6121. Min Range: -7.6121

Max Act: 4.0811. Min Act: -0.0000

Data Index: 1066972 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 7.6121. Min Range: -7.6121

Max Act: 4.2330. Min Act: -0.0000

Data Index: 501785 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 7.6121. Min Range: -7.6121

Max Act: 5.4273. Min Act: -0.0001

Data Index: 271102 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 7.6121. Min Range: -7.6121

Max Act: 3.6869. Min Act: -0.0000

Data Index: 781325 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 7.6121. Min Range: -7.6121

Max Act: 3.5479. Min Act: -0.0001

Data Index: 304425 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 7.6121. Min Range: -7.6121

Max Act: 3.2068. Min Act: -0.0000

Data Index: 554294 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 7.6121. Min Range: -7.6121

Max Act: 3.4684. Min Act: -0.0000

Data Index: 490410 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 7.6121. Min Range: -7.6121

Max Act: 2.9937. Min Act: -0.0000

Data Index: 764441 (C4 (Web Text))

Max Activating Token Index: 186