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

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

Neuron 208 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: 0.1894. Min Range: -0.1894

Max Act: 0.1894. Min Act: -0.0001

Data Index: 176136 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1667. Min Act: -0.0001

Data Index: 669256 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1623. Min Act: -0.0001

Data Index: 811655 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1620. Min Act: -0.0001

Data Index: 786711 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1615. Min Act: -0.0001

Data Index: 225863 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1617. Min Act: -0.0001

Data Index: 111634 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1565. Min Act: -0.0001

Data Index: 1219893 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1605. Min Act: -0.0001

Data Index: 75822 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1261732 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1524. Min Act: -0.0001

Data Index: 286153 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1519. Min Act: -0.0001

Data Index: 1169285 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1515. Min Act: -0.0001

Data Index: 908301 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1489. Min Act: -0.0001

Data Index: 426578 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1040863 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1483. Min Act: -0.0001

Data Index: 662785 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1472. Min Act: -0.0001

Data Index: 233380 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1465. Min Act: -0.0001

Data Index: 648712 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1411. Min Act: -0.0001

Data Index: 969817 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1126968 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.1894. Min Range: -0.1894

Max Act: 0.1400. Min Act: -0.0001

Data Index: 466143 (C4 (Web Text))

Max Activating Token Index: 348