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

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

Neuron 4791 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: 0.5350. Min Range: -0.5350

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1396800 (Python Code)

Max Activating Token Index: 217

Text #1

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1387548 (Python Code)

Max Activating Token Index: 386

Text #2

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1419618 (Python Code)

Max Activating Token Index: 468

Text #3

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1578473 (Python Code)

Max Activating Token Index: 118

Text #4

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.5207. Min Act: -0.0000

Data Index: 1453581 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4600. Min Act: -0.0001

Data Index: 1552997 (Python Code)

Max Activating Token Index: 205

Text #6

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1575467 (Python Code)

Max Activating Token Index: 253

Text #7

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1565933 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1437793 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1438797 (Python Code)

Max Activating Token Index: 423

Text #10

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1461327 (Python Code)

Max Activating Token Index: 134

Text #11

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1620561 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1414771 (Python Code)

Max Activating Token Index: 729

Text #13

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1487686 (Python Code)

Max Activating Token Index: 498

Text #14

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1562898 (Python Code)

Max Activating Token Index: 670

Text #15

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1651753 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1491904 (Python Code)

Max Activating Token Index: 657

Text #17

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1565299 (Python Code)

Max Activating Token Index: 798

Text #18

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3787. Min Act: -0.0000

Data Index: 1389007 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1500353 (Python Code)

Max Activating Token Index: 456