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

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

Neuron 2304 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1002697 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1421541 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1535071 (Python Code)

Max Activating Token Index: 217

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0629. Min Act: -0.0000

Data Index: 21098 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0614. Min Act: -0.0000

Data Index: 209046 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0585. Min Act: -0.0000

Data Index: 373409 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1306888 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1362661 (Python Code)

Max Activating Token Index: 82

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0563. Min Act: -0.0000

Data Index: 900050 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1485396 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0503. Min Act: -0.0000

Data Index: 851619 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1265508 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1509655 (Python Code)

Max Activating Token Index: 905

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0507. Min Act: -0.0000

Data Index: 230218 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0525. Min Act: -0.0000

Data Index: 388505 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1550294 (Python Code)

Max Activating Token Index: 984

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0514. Min Act: -0.0000

Data Index: 902085 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1634481 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0529. Min Act: -0.0000

Data Index: 608740 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0514. Min Act: -0.0000

Data Index: 787537 (C4 (Web Text))

Max Activating Token Index: 148