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

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

Neuron 4672 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1130179 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.6298. Min Act: -0.0000

Data Index: 611713 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5774. Min Act: -0.0000

Data Index: 474006 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5844. Min Act: -0.0000

Data Index: 539579 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.6045. Min Act: -0.0000

Data Index: 11941 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5755. Min Act: -0.0000

Data Index: 28240 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5602. Min Act: -0.0000

Data Index: 918619 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5549. Min Act: -0.0000

Data Index: 263079 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5477. Min Act: -0.0000

Data Index: 879092 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1214295 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5453. Min Act: -0.0000

Data Index: 600698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5147. Min Act: -0.0000

Data Index: 110622 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5301. Min Act: -0.0000

Data Index: 102991 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5429. Min Act: -0.0000

Data Index: 855954 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5296. Min Act: -0.0000

Data Index: 109026 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1057017 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5231. Min Act: 0.0001

Data Index: 333706 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.5249. Min Act: -0.0000

Data Index: 943348 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1281067 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.7684. Min Range: -0.7684

Max Act: 0.4919. Min Act: 0.0001

Data Index: 1231179 (C4 (Web Text))

Max Activating Token Index: 76