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

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

Neuron 970 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5474. Min Act: -0.0000

Data Index: 959185 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5330. Min Act: -0.0000

Data Index: 360731 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1300417 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4685. Min Act: -0.0000

Data Index: 709461 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5076. Min Act: -0.0001

Data Index: 545917 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1344738 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.5068. Min Act: -0.0001

Data Index: 105876 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4879. Min Act: -0.0000

Data Index: 311885 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4659. Min Act: -0.0000

Data Index: 441766 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4405. Min Act: -0.0000

Data Index: 189479 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4753. Min Act: -0.0000

Data Index: 694059 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4581. Min Act: -0.0000

Data Index: 533639 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4445. Min Act: -0.0000

Data Index: 226566 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1077166 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4259. Min Act: -0.0000

Data Index: 368066 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4889. Min Act: -0.0000

Data Index: 149090 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4074. Min Act: -0.0000

Data Index: 354770 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4220. Min Act: -0.0000

Data Index: 33409 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4367. Min Act: -0.0000

Data Index: 930747 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.5474. Min Range: -0.5474

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1240441 (C4 (Web Text))

Max Activating Token Index: 12