Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3926 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.6551. Min Range: -3.6551

Max Act: 3.6551. Min Act: -0.0001

Data Index: 947607 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.9419. Min Act: -0.0001

Data Index: 1256370 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 3.6551. Min Range: -3.6551

Max Act: 3.1783. Min Act: -0.0001

Data Index: 287893 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.8242. Min Act: -0.0001

Data Index: 1257556 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.9548. Min Act: -0.0001

Data Index: 718423 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 3.6551. Min Range: -3.6551

Max Act: 3.0369. Min Act: -0.0001

Data Index: 141467 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.8924. Min Act: -0.0001

Data Index: 441596 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.8993. Min Act: -0.0001

Data Index: 1127223 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.6087. Min Act: -0.0001

Data Index: 844209 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.7694. Min Act: -0.0001

Data Index: 680137 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 3.6551. Min Range: -3.6551

Max Act: 3.0096. Min Act: -0.0001

Data Index: 416186 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.8629. Min Act: -0.0001

Data Index: 1099244 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.8398. Min Act: -0.0001

Data Index: 78588 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.7828. Min Act: -0.0001

Data Index: 1341656 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.8105. Min Act: -0.0001

Data Index: 392126 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.7652. Min Act: -0.0001

Data Index: 1262961 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.7159. Min Act: -0.0001

Data Index: 182717 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.5633. Min Act: -0.0001

Data Index: 420928 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.8019. Min Act: -0.0001

Data Index: 630411 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 3.6551. Min Range: -3.6551

Max Act: 2.5402. Min Act: -0.0001

Data Index: 712820 (C4 (Web Text))

Max Activating Token Index: 10