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

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

Neuron 706 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: 0.1905. Min Range: -0.1905

Max Act: 0.1905. Min Act: -0.0001

Data Index: 770328 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1666. Min Act: -0.0001

Data Index: 684036 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1676. Min Act: -0.0001

Data Index: 403086 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1626. Min Act: -0.0001

Data Index: 858523 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1606. Min Act: -0.0001

Data Index: 316114 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1594. Min Act: -0.0001

Data Index: 863234 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1598. Min Act: -0.0001

Data Index: 146133 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1581. Min Act: -0.0001

Data Index: 262958 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1467. Min Act: -0.0001

Data Index: 911667 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1497. Min Act: -0.0001

Data Index: 570470 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1485. Min Act: -0.0001

Data Index: 535259 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1542. Min Act: -0.0001

Data Index: 252147 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1431. Min Act: -0.0001

Data Index: 464674 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1486. Min Act: -0.0001

Data Index: 846384 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1044066 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1404. Min Act: -0.0001

Data Index: 916851 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1447. Min Act: -0.0001

Data Index: 589028 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1387. Min Act: -0.0001

Data Index: 693051 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1439. Min Act: -0.0001

Data Index: 409163 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1438. Min Act: -0.0001

Data Index: 420781 (C4 (Web Text))

Max Activating Token Index: 112