Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2504 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.8987. Min Act: -0.0000

Data Index: 686893 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.8400. Min Act: -0.0000

Data Index: 907582 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.7490. Min Act: -0.0000

Data Index: 447231 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.7712. Min Act: -0.0000

Data Index: 745324 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.7214. Min Act: -0.0000

Data Index: 386288 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1276050 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1015353 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.6655. Min Act: -0.0000

Data Index: 491158 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1456065 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1057462 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.6858. Min Act: -0.0000

Data Index: 257145 (C4 (Web Text))

Max Activating Token Index: 100

Text #11

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.6188. Min Act: -0.0000

Data Index: 199242 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.6198. Min Act: -0.0000

Data Index: 265094 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.6375. Min Act: -0.0000

Data Index: 448883 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.6170. Min Act: -0.0000

Data Index: 983590 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.5754. Min Act: -0.0000

Data Index: 171147 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.5869. Min Act: -0.0000

Data Index: 209231 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1063521 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.5448. Min Act: -0.0000

Data Index: 963954 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.8987. Min Range: -0.8987

Max Act: 0.5578. Min Act: -0.0000

Data Index: 114413 (C4 (Web Text))

Max Activating Token Index: 685