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

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

Neuron 3009 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: 2.2346. Min Range: -2.2346

Max Act: 2.2346. Min Act: -0.0000

Data Index: 1586780 (Python Code)

Max Activating Token Index: 673

Text #1

Max Range: 2.2346. Min Range: -2.2346

Max Act: 2.1426. Min Act: -0.0000

Data Index: 1521048 (Python Code)

Max Activating Token Index: 710

Text #2

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1476020 (Python Code)

Max Activating Token Index: 548

Text #3

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.9039. Min Act: -0.0000

Data Index: 1476195 (Python Code)

Max Activating Token Index: 687

Text #4

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.8782. Min Act: -0.0000

Data Index: 1431358 (Python Code)

Max Activating Token Index: 426

Text #5

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.8423. Min Act: -0.0000

Data Index: 1560165 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.7121. Min Act: -0.0000

Data Index: 1489054 (Python Code)

Max Activating Token Index: 439

Text #7

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.6283. Min Act: -0.0000

Data Index: 1458321 (Python Code)

Max Activating Token Index: 411

Text #8

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.5794. Min Act: -0.0000

Data Index: 1506569 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.6028. Min Act: -0.0000

Data Index: 1496062 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.4630. Min Act: -0.0000

Data Index: 1576243 (Python Code)

Max Activating Token Index: 83

Text #11

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.4826. Min Act: -0.0000

Data Index: 1378822 (Python Code)

Max Activating Token Index: 618

Text #12

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.5138. Min Act: -0.0000

Data Index: 1616200 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.4286. Min Act: -0.0000

Data Index: 1506750 (Python Code)

Max Activating Token Index: 174

Text #14

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.4606. Min Act: -0.0000

Data Index: 1488150 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.2961. Min Act: -0.0000

Data Index: 1516450 (Python Code)

Max Activating Token Index: 56

Text #16

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1552642 (Python Code)

Max Activating Token Index: 902

Text #17

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1530371 (Python Code)

Max Activating Token Index: 751

Text #18

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.3349. Min Act: -0.0000

Data Index: 1445524 (Python Code)

Max Activating Token Index: 888

Text #19

Max Range: 2.2346. Min Range: -2.2346

Max Act: 1.2369. Min Act: -0.0000

Data Index: 1479143 (Python Code)

Max Activating Token Index: 741