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

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

Neuron 2749 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.5663. Min Act: -0.0001

Data Index: 734838 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.3870. Min Act: -0.0001

Data Index: 1051797 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2152. Min Act: -0.0001

Data Index: 134509 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2807. Min Act: -0.0001

Data Index: 470681 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.3068. Min Act: -0.0001

Data Index: 173380 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2029. Min Act: -0.0001

Data Index: 954919 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.3124. Min Act: -0.0001

Data Index: 213693 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2701. Min Act: -0.0001

Data Index: 345537 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1290. Min Act: -0.0001

Data Index: 761627 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1979. Min Act: -0.0001

Data Index: 638603 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1973. Min Act: -0.0001

Data Index: 1262831 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1936. Min Act: -0.0001

Data Index: 1106174 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1803. Min Act: -0.0001

Data Index: 240460 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1453. Min Act: -0.0001

Data Index: 963155 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2465. Min Act: -0.0001

Data Index: 745930 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.2237. Min Act: -0.0001

Data Index: 726629 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1528. Min Act: -0.0001

Data Index: 439521 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1507. Min Act: -0.0001

Data Index: 257615 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1206. Min Act: -0.0001

Data Index: 123772 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.5663. Min Range: -1.5663

Max Act: 1.1668. Min Act: -0.0001

Data Index: 1235791 (C4 (Web Text))

Max Activating Token Index: 962