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

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

Neuron 3939 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.9311. Min Act: -0.0000

Data Index: 139899 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.5204. Min Act: -0.0000

Data Index: 841543 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.5153. Min Act: -0.0000

Data Index: 1422434 (Python Code)

Max Activating Token Index: 361

Text #3

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.5523. Min Act: -0.0000

Data Index: 1522307 (Python Code)

Max Activating Token Index: 699

Text #4

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1469581 (Python Code)

Max Activating Token Index: 740

Text #5

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.5946. Min Act: -0.0000

Data Index: 1562169 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1394961 (Python Code)

Max Activating Token Index: 721

Text #7

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1569755 (Python Code)

Max Activating Token Index: 280

Text #8

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1372200 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1452901 (Python Code)

Max Activating Token Index: 724

Text #10

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.2954. Min Act: -0.0000

Data Index: 1505066 (Python Code)

Max Activating Token Index: 649

Text #11

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.3693. Min Act: -0.0000

Data Index: 1367628 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1525742 (Python Code)

Max Activating Token Index: 464

Text #13

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1361118 (Python Code)

Max Activating Token Index: 693

Text #14

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.2977. Min Act: -0.0000

Data Index: 1587688 (Python Code)

Max Activating Token Index: 909

Text #15

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.2594. Min Act: -0.0000

Data Index: 1636895 (Python Code)

Max Activating Token Index: 625

Text #16

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.2527. Min Act: -0.0000

Data Index: 1589677 (Python Code)

Max Activating Token Index: 506

Text #17

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.3351. Min Act: -0.0000

Data Index: 1576174 (Python Code)

Max Activating Token Index: 572

Text #18

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1446463 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 1.9311. Min Range: -1.9311

Max Act: 1.2582. Min Act: -0.0000

Data Index: 1384695 (Python Code)

Max Activating Token Index: 530