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

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

Neuron 3708 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.3759. Min Act: -0.0000

Data Index: 219286 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.2034. Min Act: -0.0000

Data Index: 342997 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9613. Min Act: -0.0000

Data Index: 336358 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0351. Min Act: -0.0000

Data Index: 182688 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1176701 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1147585 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8884. Min Act: -0.0000

Data Index: 28910 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8393. Min Act: -0.0000

Data Index: 531930 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.7796. Min Act: -0.0000

Data Index: 242678 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8377. Min Act: -0.0000

Data Index: 280683 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8644. Min Act: -0.0000

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8217. Min Act: -0.0000

Data Index: 134938 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8353. Min Act: -0.0000

Data Index: 282667 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.7937. Min Act: -0.0000

Data Index: 832392 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.7144. Min Act: -0.0000

Data Index: 722416 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.7553. Min Act: -0.0000

Data Index: 878463 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8026. Min Act: -0.0000

Data Index: 911573 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.7807. Min Act: -0.0000

Data Index: 448801 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.8034. Min Act: -0.0000

Data Index: 87731 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 1.3759. Min Range: -1.3759

Max Act: 0.7342. Min Act: -0.0000

Data Index: 203045 (C4 (Web Text))

Max Activating Token Index: 793