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

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

Neuron 3154 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5567. Min Act: -0.0000

Data Index: 329882 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.5241. Min Act: -0.0000

Data Index: 373701 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4826. Min Act: -0.0000

Data Index: 619494 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4243. Min Act: -0.0000

Data Index: 84610 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1331580 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1314717 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4095. Min Act: -0.0000

Data Index: 190977 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1359294 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1131782 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3876. Min Act: -0.0000

Data Index: 428540 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3623. Min Act: -0.0000

Data Index: 874857 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1195260 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3316. Min Act: -0.0000

Data Index: 475944 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3407. Min Act: -0.0000

Data Index: 783253 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1062071 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3186. Min Act: -0.0000

Data Index: 953837 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3127. Min Act: -0.0000

Data Index: 235331 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3077. Min Act: -0.0000

Data Index: 937654 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3118. Min Act: -0.0000

Data Index: 773725 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.5567. Min Range: -0.5567

Max Act: 0.3204. Min Act: -0.0000

Data Index: 525749 (C4 (Web Text))

Max Activating Token Index: 754