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

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

Neuron 3190 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: 1.1758. Min Range: -1.1758

Max Act: 1.1758. Min Act: -0.0001

Data Index: 734836 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.1268. Min Act: -0.0001

Data Index: 1063082 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.1040. Min Act: -0.0001

Data Index: 592808 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0664. Min Act: -0.0001

Data Index: 1356429 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0502. Min Act: -0.0001

Data Index: 764943 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0310. Min Act: -0.0001

Data Index: 364298 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0416. Min Act: -0.0001

Data Index: 836367 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0443. Min Act: -0.0001

Data Index: 1285705 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0459. Min Act: -0.0001

Data Index: 1198422 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0295. Min Act: -0.0001

Data Index: 59816 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0413. Min Act: -0.0001

Data Index: 550653 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0191. Min Act: -0.0001

Data Index: 229452 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0102. Min Act: -0.0001

Data Index: 1047477 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.1758. Min Range: -1.1758

Max Act: 1.0054. Min Act: -0.0001

Data Index: 1107592 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9991. Min Act: -0.0001

Data Index: 609699 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9776. Min Act: -0.0001

Data Index: 675441 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9294. Min Act: -0.0001

Data Index: 1349239 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9835. Min Act: -0.0001

Data Index: 1338658 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.9197. Min Act: -0.0001

Data Index: 113135 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 1.1758. Min Range: -1.1758

Max Act: 0.8662. Min Act: -0.0001

Data Index: 336158 (C4 (Web Text))

Max Activating Token Index: 822