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

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

Neuron 1950 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: 5.5142. Min Range: -5.5142

Max Act: 5.5142. Min Act: -0.0000

Data Index: 1520925 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 5.5142. Min Range: -5.5142

Max Act: 4.5044. Min Act: -0.0000

Data Index: 1472444 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 5.5142. Min Range: -5.5142

Max Act: 4.4961. Min Act: -0.0000

Data Index: 1428061 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 5.5142. Min Range: -5.5142

Max Act: 4.2211. Min Act: -0.0000

Data Index: 1590653 (Python Code)

Max Activating Token Index: 725

Text #4

Max Range: 5.5142. Min Range: -5.5142

Max Act: 4.2118. Min Act: -0.0000

Data Index: 1475126 (Python Code)

Max Activating Token Index: 756

Text #5

Max Range: 5.5142. Min Range: -5.5142

Max Act: 4.1261. Min Act: -0.0000

Data Index: 1539184 (Python Code)

Max Activating Token Index: 933

Text #6

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.8929. Min Act: -0.0000

Data Index: 1439544 (Python Code)

Max Activating Token Index: 774

Text #7

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.8281. Min Act: -0.0000

Data Index: 1462788 (Python Code)

Max Activating Token Index: 402

Text #8

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.9574. Min Act: -0.0000

Data Index: 1545645 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.8459. Min Act: -0.0000

Data Index: 1608509 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.5400. Min Act: -0.0000

Data Index: 1456436 (Python Code)

Max Activating Token Index: 354

Text #11

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.6743. Min Act: -0.0000

Data Index: 1630569 (Python Code)

Max Activating Token Index: 719

Text #12

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.2786. Min Act: -0.0000

Data Index: 1445042 (Python Code)

Max Activating Token Index: 787

Text #13

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.5417. Min Act: -0.0000

Data Index: 1424048 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.4915. Min Act: -0.0000

Data Index: 1578367 (Python Code)

Max Activating Token Index: 134

Text #15

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.4607. Min Act: -0.0000

Data Index: 1642986 (Python Code)

Max Activating Token Index: 773

Text #16

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.2480. Min Act: -0.0000

Data Index: 1593767 (Python Code)

Max Activating Token Index: 634

Text #17

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.3335. Min Act: -0.0000

Data Index: 1583845 (Python Code)

Max Activating Token Index: 303

Text #18

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.1482. Min Act: -0.0000

Data Index: 1616896 (Python Code)

Max Activating Token Index: 846

Text #19

Max Range: 5.5142. Min Range: -5.5142

Max Act: 3.2372. Min Act: -0.0000

Data Index: 1592574 (Python Code)

Max Activating Token Index: 94