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

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

Neuron 2675 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1773. Min Act: -0.0001

Data Index: 1012553 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1707. Min Act: -0.0001

Data Index: 659909 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1516. Min Act: -0.0001

Data Index: 162640 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1626. Min Act: -0.0001

Data Index: 367395 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1541. Min Act: -0.0001

Data Index: 1223714 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1548. Min Act: -0.0001

Data Index: 685162 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1269757 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1372. Min Act: -0.0001

Data Index: 741561 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1439. Min Act: -0.0001

Data Index: 144939 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1411. Min Act: -0.0001

Data Index: 668035 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1410. Min Act: -0.0001

Data Index: 948297 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1359. Min Act: -0.0001

Data Index: 3227 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1251. Min Act: -0.0001

Data Index: 424019 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1369. Min Act: -0.0001

Data Index: 51209 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1030534 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1235. Min Act: -0.0001

Data Index: 753439 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1349. Min Act: -0.0001

Data Index: 522022 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1292. Min Act: -0.0001

Data Index: 73138 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1031117 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1302. Min Act: -0.0001

Data Index: 280708 (C4 (Web Text))

Max Activating Token Index: 183