Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 305 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1372. Min Act: -0.0001

Data Index: 150185 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0001

Data Index: 676704 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1507. Min Act: -0.0001

Data Index: 647177 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1485. Min Act: -0.0001

Data Index: 400626 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1487. Min Act: -0.0001

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0951. Min Act: -0.0001

Data Index: 548250 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1454. Min Act: -0.0001

Data Index: 158570 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1370. Min Act: -0.0001

Data Index: 876305 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1335. Min Act: -0.0001

Data Index: 142110 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1270561 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1136661 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1401. Min Act: -0.0001

Data Index: 396595 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1415. Min Act: -0.0001

Data Index: 282145 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1319. Min Act: -0.0001

Data Index: 424063 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1330. Min Act: -0.0001

Data Index: 809385 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1377. Min Act: -0.0001

Data Index: 293416 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1383. Min Act: -0.0001

Data Index: 324347 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1495. Min Act: -0.0001

Data Index: 133888 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1288. Min Act: -0.0001

Data Index: 406022 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1346. Min Act: -0.0001

Data Index: 145196 (C4 (Web Text))

Max Activating Token Index: 113