Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2846 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.1594. Min Act: -0.0001

Data Index: 1590919 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.4408. Min Act: -0.0000

Data Index: 1531221 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.1233. Min Act: -0.0001

Data Index: 1380198 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.2570. Min Act: -0.0001

Data Index: 1621502 (Python Code)

Max Activating Token Index: 613

Text #4

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.2428. Min Act: -0.0001

Data Index: 1631670 (Python Code)

Max Activating Token Index: 745

Text #5

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.1390. Min Act: -0.0001

Data Index: 1559766 (Python Code)

Max Activating Token Index: 449

Text #6

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.0872. Min Act: -0.0001

Data Index: 1364817 (Python Code)

Max Activating Token Index: 816

Text #7

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.0747. Min Act: -0.0001

Data Index: 1630134 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 3.4408. Min Range: -3.4408

Max Act: 3.1294. Min Act: -0.0001

Data Index: 1633644 (Python Code)

Max Activating Token Index: 655

Text #9

Max Range: 3.4408. Min Range: -3.4408

Max Act: 2.9548. Min Act: -0.0001

Data Index: 1446761 (Python Code)

Max Activating Token Index: 738

Text #10

Max Range: 3.4408. Min Range: -3.4408

Max Act: 2.0196. Min Act: -0.0001

Data Index: 1631787 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.9168. Min Act: -0.0001

Data Index: 1652730 (Python Code)

Max Activating Token Index: 901

Text #12

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.5588. Min Act: -0.0001

Data Index: 1369218 (Python Code)

Max Activating Token Index: 665

Text #13

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.5665. Min Act: -0.0001

Data Index: 1505997 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.4582. Min Act: -0.0000

Data Index: 557805 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.4574. Min Act: -0.0000

Data Index: 1080939 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.3626. Min Act: -0.0000

Data Index: 1523090 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.4073. Min Act: -0.0001

Data Index: 1578961 (Python Code)

Max Activating Token Index: 362

Text #18

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.4154. Min Act: -0.0000

Data Index: 1655846 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 3.4408. Min Range: -3.4408

Max Act: 1.4201. Min Act: -0.0001

Data Index: 1459227 (Python Code)

Max Activating Token Index: 795