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

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

Neuron 1121 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: 1.4496. Min Range: -1.4496

Max Act: 1.4496. Min Act: -0.0000

Data Index: 1272023 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1383276 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1558364 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1517437 (Python Code)

Max Activating Token Index: 362

Text #4

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1373324 (Python Code)

Max Activating Token Index: 859

Text #5

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1551378 (Python Code)

Max Activating Token Index: 190

Text #6

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1633022 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1649071 (Python Code)

Max Activating Token Index: 1007

Text #8

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1038543 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1765. Min Act: -0.0000

Data Index: 1600942 (Python Code)

Max Activating Token Index: 626

Text #10

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1504991 (Python Code)

Max Activating Token Index: 964

Text #11

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2474. Min Act: -0.0000

Data Index: 210840 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1496058 (Python Code)

Max Activating Token Index: 690

Text #13

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2384. Min Act: -0.0000

Data Index: 1571705 (Python Code)

Max Activating Token Index: 790

Text #14

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2176. Min Act: -0.0000

Data Index: 1363119 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2877. Min Act: -0.0000

Data Index: 109810 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.2126. Min Act: -0.0000

Data Index: 1405058 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1572788 (Python Code)

Max Activating Token Index: 899

Text #18

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1364730 (Python Code)

Max Activating Token Index: 770

Text #19

Max Range: 1.4496. Min Range: -1.4496

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1410706 (Python Code)

Max Activating Token Index: 869