Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2579 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.9237. Min Act: -0.0000

Data Index: 1467891 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.7942. Min Act: -0.0000

Data Index: 1521193 (Python Code)

Max Activating Token Index: 64

Text #2

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.7615. Min Act: -0.0000

Data Index: 1432218 (Python Code)

Max Activating Token Index: 163

Text #3

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.6512. Min Act: -0.0000

Data Index: 1550893 (Python Code)

Max Activating Token Index: 625

Text #4

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.6015. Min Act: -0.0000

Data Index: 1580261 (Python Code)

Max Activating Token Index: 485

Text #5

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.4766. Min Act: -0.0000

Data Index: 1417632 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.6847. Min Act: -0.0000

Data Index: 1438089 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.5259. Min Act: -0.0000

Data Index: 1473970 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.4472. Min Act: -0.0000

Data Index: 1587838 (Python Code)

Max Activating Token Index: 334

Text #9

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.4358. Min Act: -0.0000

Data Index: 1375275 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.2920. Min Act: -0.0000

Data Index: 1362459 (Python Code)

Max Activating Token Index: 874

Text #11

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.3885. Min Act: -0.0000

Data Index: 1109440 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.3687. Min Act: -0.0000

Data Index: 1611663 (Python Code)

Max Activating Token Index: 293

Text #13

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.3792. Min Act: -0.0000

Data Index: 1461804 (Python Code)

Max Activating Token Index: 319

Text #14

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.4999. Min Act: -0.0000

Data Index: 1530392 (Python Code)

Max Activating Token Index: 412

Text #15

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.3570. Min Act: -0.0000

Data Index: 1527599 (Python Code)

Max Activating Token Index: 701

Text #16

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.2376. Min Act: -0.0000

Data Index: 1517659 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.3339. Min Act: -0.0000

Data Index: 174186 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.3045. Min Act: -0.0000

Data Index: 1525194 (Python Code)

Max Activating Token Index: 533

Text #19

Max Range: 2.9237. Min Range: -2.9237

Max Act: 2.3025. Min Act: -0.0000

Data Index: 1639585 (Python Code)

Max Activating Token Index: 302