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

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

Neuron 3574 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.7119. Min Act: -0.0002

Data Index: 691990 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.5426. Min Act: -0.0002

Data Index: 174788 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.3493. Min Act: -0.0001

Data Index: 264583 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.4635. Min Act: -0.0002

Data Index: 239551 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.4798. Min Act: -0.0002

Data Index: 1329297 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.4247. Min Act: -0.0002

Data Index: 31291 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.3387. Min Act: -0.0002

Data Index: 887601 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.3643. Min Act: -0.0001

Data Index: 213231 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.3933. Min Act: -0.0001

Data Index: 744937 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2070. Min Act: -0.0001

Data Index: 894064 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.1953. Min Act: -0.0001

Data Index: 645537 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.1901. Min Act: -0.0001

Data Index: 625024 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2877. Min Act: -0.0001

Data Index: 1054904 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2770. Min Act: -0.0001

Data Index: 1131429 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2335. Min Act: -0.0001

Data Index: 1199459 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2251. Min Act: -0.0001

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2612. Min Act: -0.0001

Data Index: 31721 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2633. Min Act: -0.0002

Data Index: 1112012 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2172. Min Act: -0.0002

Data Index: 524087 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 1.7119. Min Range: -1.7119

Max Act: 1.2796. Min Act: -0.0001

Data Index: 704016 (C4 (Web Text))

Max Activating Token Index: 333