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

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

Neuron 4492 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.2166. Min Act: -0.0000

Data Index: 675268 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9419. Min Act: 0.0000

Data Index: 284001 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9446. Min Act: 0.0000

Data Index: 164862 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8822. Min Act: 0.0002

Data Index: 322444 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8325. Min Act: -0.0000

Data Index: 804359 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8244. Min Act: -0.0000

Data Index: 1143814 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8614. Min Act: 0.0000

Data Index: 746994 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8646. Min Act: -0.0000

Data Index: 195017 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9152. Min Act: -0.0000

Data Index: 305341 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8600. Min Act: 0.0002

Data Index: 582107 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7986. Min Act: 0.0001

Data Index: 1250397 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8107. Min Act: -0.0000

Data Index: 207689 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7798. Min Act: -0.0000

Data Index: 622481 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7706. Min Act: 0.0000

Data Index: 537523 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7420. Min Act: -0.0000

Data Index: 871614 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1324703 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7360. Min Act: -0.0000

Data Index: 35482 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7143. Min Act: -0.0000

Data Index: 216821 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7092. Min Act: 0.0002

Data Index: 905764 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.7655. Min Act: -0.0000

Data Index: 257574 (C4 (Web Text))

Max Activating Token Index: 833