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

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

Neuron 2681 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3619. Min Act: -0.0000

Data Index: 860899 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3388. Min Act: -0.0000

Data Index: 591784 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1168887 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2471. Min Act: -0.0001

Data Index: 801545 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2683. Min Act: -0.0000

Data Index: 990913 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2317. Min Act: -0.0000

Data Index: 547057 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1236313 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2293. Min Act: -0.0000

Data Index: 125676 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2174. Min Act: -0.0000

Data Index: 874373 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2195. Min Act: -0.0001

Data Index: 563363 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2265. Min Act: -0.0001

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2126. Min Act: -0.0000

Data Index: 469206 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2160. Min Act: -0.0000

Data Index: 694565 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1159157 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2144. Min Act: -0.0001

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2212. Min Act: -0.0001

Data Index: 150239 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2126. Min Act: -0.0001

Data Index: 605705 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2184. Min Act: -0.0000

Data Index: 995662 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.3619. Min Range: -0.3619

Max Act: 0.2116. Min Act: -0.0001

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 863