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

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

Neuron 5697 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: 2.0149. Min Range: -2.0149

Max Act: 2.0149. Min Act: -0.0000

Data Index: 1481816 (Python Code)

Max Activating Token Index: 195

Text #1

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.8965. Min Act: -0.0000

Data Index: 1520262 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.8569. Min Act: -0.0000

Data Index: 1656193 (Python Code)

Max Activating Token Index: 921

Text #3

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.7146. Min Act: -0.0000

Data Index: 1592175 (Python Code)

Max Activating Token Index: 286

Text #4

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.9232. Min Act: -0.0000

Data Index: 1478208 (Python Code)

Max Activating Token Index: 574

Text #5

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6730. Min Act: -0.0000

Data Index: 1627882 (Python Code)

Max Activating Token Index: 652

Text #6

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1366881 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1371154 (Python Code)

Max Activating Token Index: 549

Text #8

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.7451. Min Act: -0.0000

Data Index: 1563052 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6332. Min Act: -0.0000

Data Index: 1604255 (Python Code)

Max Activating Token Index: 438

Text #10

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1363856 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1373656 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1648065 (Python Code)

Max Activating Token Index: 334

Text #13

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6929. Min Act: -0.0000

Data Index: 1432320 (Python Code)

Max Activating Token Index: 203

Text #14

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1589449 (Python Code)

Max Activating Token Index: 343

Text #15

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6742. Min Act: -0.0000

Data Index: 1377204 (Python Code)

Max Activating Token Index: 787

Text #16

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6537. Min Act: -0.0000

Data Index: 1527503 (Python Code)

Max Activating Token Index: 817

Text #17

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.5174. Min Act: -0.0000

Data Index: 1554801 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.6618. Min Act: -0.0000

Data Index: 1381354 (Python Code)

Max Activating Token Index: 179

Text #19

Max Range: 2.0149. Min Range: -2.0149

Max Act: 1.5608. Min Act: -0.0000

Data Index: 1608120 (Python Code)

Max Activating Token Index: 369