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

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

Neuron 1789 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: 0.1963. Min Range: -0.1963

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1217362 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1819. Min Act: -0.0001

Data Index: 354893 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1553300 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1745. Min Act: -0.0001

Data Index: 696021 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1680. Min Act: -0.0001

Data Index: 839487 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1640. Min Act: -0.0001

Data Index: 710725 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1532. Min Act: -0.0001

Data Index: 237282 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1517. Min Act: -0.0001

Data Index: 732309 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1591. Min Act: -0.0001

Data Index: 369521 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1521. Min Act: -0.0001

Data Index: 966881 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1150749 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1498. Min Act: -0.0001

Data Index: 632028 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1391. Min Act: -0.0001

Data Index: 747763 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1443. Min Act: -0.0001

Data Index: 1153291 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1527. Min Act: -0.0001

Data Index: 247852 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1378. Min Act: -0.0001

Data Index: 417014 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1378. Min Act: -0.0001

Data Index: 796953 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1300. Min Act: -0.0001

Data Index: 176072 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1330. Min Act: -0.0001

Data Index: 110552 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.1963. Min Range: -0.1963

Max Act: 0.1350. Min Act: -0.0001

Data Index: 983712 (C4 (Web Text))

Max Activating Token Index: 485