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

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

Neuron 282 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.4374. Min Act: -0.0001

Data Index: 1138443 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.2083. Min Act: -0.0001

Data Index: 1335409 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.0938. Min Act: -0.0001

Data Index: 1192855 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.1571. Min Act: -0.0001

Data Index: 1035206 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.1032. Min Act: -0.0001

Data Index: 1437113 (Python Code)

Max Activating Token Index: 757

Text #5

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.1705. Min Act: -0.0001

Data Index: 319271 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.0090. Min Act: -0.0001

Data Index: 237425 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.4374. Min Range: -1.4374

Max Act: 0.9681. Min Act: -0.0001

Data Index: 502224 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.0732. Min Act: -0.0001

Data Index: 1386380 (Python Code)

Max Activating Token Index: 745

Text #9

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.0138. Min Act: -0.0001

Data Index: 602497 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.0422. Min Act: -0.0001

Data Index: 95041 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 1.4374. Min Range: -1.4374

Max Act: 0.9633. Min Act: -0.0001

Data Index: 243560 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 1.4374. Min Range: -1.4374

Max Act: 0.9856. Min Act: -0.0001

Data Index: 1043514 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.0066. Min Act: -0.0001

Data Index: 1524888 (Python Code)

Max Activating Token Index: 272

Text #14

Max Range: 1.4374. Min Range: -1.4374

Max Act: 1.0188. Min Act: -0.0001

Data Index: 1437876 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 1.4374. Min Range: -1.4374

Max Act: 0.9822. Min Act: -0.0001

Data Index: 1363292 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 1.4374. Min Range: -1.4374

Max Act: 0.9850. Min Act: -0.0001

Data Index: 1466589 (Python Code)

Max Activating Token Index: 193

Text #17

Max Range: 1.4374. Min Range: -1.4374

Max Act: 0.9500. Min Act: -0.0001

Data Index: 1244350 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 1.4374. Min Range: -1.4374

Max Act: 0.9576. Min Act: -0.0001

Data Index: 1625546 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 1.4374. Min Range: -1.4374

Max Act: 0.8972. Min Act: -0.0001

Data Index: 1265520 (C4 (Web Text))

Max Activating Token Index: 356