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

Dataset: The Pile

Neuron 4935 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1799. Min Range: -1.1799

Max Act: 1.1233. Min Act: -0.0000

Data Index: 669409 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 1.1799. Min Range: -1.1799

Max Act: 1.1799. Min Act: -0.0000

Data Index: 514360 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.9932. Min Act: -0.0000

Data Index: 1477958 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 1.1799. Min Range: -1.1799

Max Act: 1.0059. Min Act: -0.0000

Data Index: 720176 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.9280. Min Act: -0.0000

Data Index: 259522 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.9504. Min Act: -0.0000

Data Index: 851166 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8937. Min Act: 0.0000

Data Index: 1754326 (The Pile)

Max Activating Token Index: 652

Text #7

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8455. Min Act: -0.0000

Data Index: 14350 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1477804 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1754078 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8528. Min Act: -0.0000

Data Index: 693425 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1124093 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1907135 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1097777 (The Pile)

Max Activating Token Index: 866

Text #14

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8437. Min Act: -0.0000

Data Index: 268010 (The Pile)

Max Activating Token Index: 335

Text #15

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.7988. Min Act: 0.0001

Data Index: 1631619 (The Pile)

Max Activating Token Index: 53

Text #16

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.7936. Min Act: 0.0001

Data Index: 1251734 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1407521 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1809746 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 1.1799. Min Range: -1.1799

Max Act: 0.7747. Min Act: 0.0000

Data Index: 1298227 (The Pile)

Max Activating Token Index: 182