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

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

Neuron 1760 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.6188. Min Act: -0.0001

Data Index: 116867 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.6036. Min Act: -0.0001

Data Index: 1237080 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5823. Min Act: -0.0001

Data Index: 11047 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5610. Min Act: -0.0001

Data Index: 1351078 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5681. Min Act: -0.0001

Data Index: 1341213 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5325. Min Act: -0.0001

Data Index: 23692 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5086. Min Act: -0.0001

Data Index: 455364 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5164. Min Act: -0.0001

Data Index: 1123281 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4748. Min Act: -0.0001

Data Index: 639658 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5118. Min Act: -0.0001

Data Index: 329346 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4715. Min Act: -0.0001

Data Index: 279111 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4523. Min Act: -0.0001

Data Index: 176035 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4161. Min Act: -0.0000

Data Index: 678261 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4000. Min Act: -0.0001

Data Index: 798449 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4034. Min Act: -0.0001

Data Index: 1014995 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4019. Min Act: -0.0001

Data Index: 309300 (C4 (Web Text))

Max Activating Token Index: 368

Text #16

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.3677. Min Act: -0.0001

Data Index: 110158 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.3606. Min Act: -0.0001

Data Index: 1049562 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.3599. Min Act: -0.0001

Data Index: 240347 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.3623. Min Act: -0.0001

Data Index: 523127 (C4 (Web Text))

Max Activating Token Index: 475