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

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

Neuron 2705 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.8591. Min Act: -0.0002

Data Index: 294237 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.8582. Min Act: -0.0002

Data Index: 537831 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.8582. Min Act: -0.0002

Data Index: 1255445 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.8582. Min Act: -0.0002

Data Index: 439005 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.8283. Min Act: -0.0002

Data Index: 764138 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.8064. Min Act: -0.0002

Data Index: 918960 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.8092. Min Act: -0.0002

Data Index: 278942 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7995. Min Act: -0.0002

Data Index: 1223093 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7960. Min Act: -0.0002

Data Index: 209951 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7899. Min Act: -0.0002

Data Index: 888678 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7825. Min Act: -0.0002

Data Index: 1056428 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7860. Min Act: -0.0002

Data Index: 246 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7730. Min Act: -0.0002

Data Index: 476831 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7633. Min Act: -0.0002

Data Index: 390275 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7729. Min Act: -0.0002

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7639. Min Act: -0.0002

Data Index: 978267 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7598. Min Act: -0.0002

Data Index: 846871 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7490. Min Act: -0.0002

Data Index: 313510 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7501. Min Act: -0.0002

Data Index: 1233990 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.8591. Min Range: -0.8591

Max Act: 0.7480. Min Act: -0.0002

Data Index: 546282 (C4 (Web Text))

Max Activating Token Index: 3