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

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

Neuron 1794 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 15.5157. Min Range: -15.5157

Max Act: 15.5157. Min Act: -0.0000

Data Index: 792844 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 15.5157. Min Range: -15.5157

Max Act: 15.3129. Min Act: -0.0000

Data Index: 1188642 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 15.5157. Min Range: -15.5157

Max Act: 15.0028. Min Act: -0.0000

Data Index: 166839 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 15.5157. Min Range: -15.5157

Max Act: 15.0012. Min Act: -0.0000

Data Index: 988689 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 15.5157. Min Range: -15.5157

Max Act: 14.1667. Min Act: -0.0000

Data Index: 354385 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 15.5157. Min Range: -15.5157

Max Act: 14.1196. Min Act: -0.0000

Data Index: 1018580 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 15.5157. Min Range: -15.5157

Max Act: 14.2113. Min Act: -0.0000

Data Index: 403366 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 15.5157. Min Range: -15.5157

Max Act: 13.9695. Min Act: -0.0000

Data Index: 821949 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 15.5157. Min Range: -15.5157

Max Act: 14.1197. Min Act: -0.0000

Data Index: 586168 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 15.5157. Min Range: -15.5157

Max Act: 14.3341. Min Act: -0.0000

Data Index: 1127582 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 15.5157. Min Range: -15.5157

Max Act: 14.3052. Min Act: -0.0000

Data Index: 1220388 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 15.5157. Min Range: -15.5157

Max Act: 14.4513. Min Act: -0.0000

Data Index: 437765 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 15.5157. Min Range: -15.5157

Max Act: 14.0105. Min Act: -0.0000

Data Index: 4619 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 15.5157. Min Range: -15.5157

Max Act: 13.7832. Min Act: -0.0000

Data Index: 651414 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 15.5157. Min Range: -15.5157

Max Act: 13.8052. Min Act: -0.0000

Data Index: 1184329 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 15.5157. Min Range: -15.5157

Max Act: 13.9385. Min Act: -0.0000

Data Index: 1008981 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 15.5157. Min Range: -15.5157

Max Act: 13.7196. Min Act: -0.0000

Data Index: 707366 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 15.5157. Min Range: -15.5157

Max Act: 13.8002. Min Act: -0.0000

Data Index: 688488 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 15.5157. Min Range: -15.5157

Max Act: 13.6424. Min Act: -0.0000

Data Index: 290161 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 15.5157. Min Range: -15.5157

Max Act: 13.6273. Min Act: -0.0000

Data Index: 222902 (C4 (Web Text))

Max Activating Token Index: 375