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

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

Neuron 1695 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.9209. Min Act: -0.0000

Data Index: 1390188 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.9484. Min Act: -0.0000

Data Index: 1577752 (Python Code)

Max Activating Token Index: 537

Text #2

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.7470. Min Act: -0.0000

Data Index: 1557540 (Python Code)

Max Activating Token Index: 314

Text #3

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.6647. Min Act: -0.0000

Data Index: 1397600 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.6069. Min Act: -0.0000

Data Index: 1490983 (Python Code)

Max Activating Token Index: 371

Text #5

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.5927. Min Act: -0.0000

Data Index: 604549 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.6671. Min Act: -0.0000

Data Index: 1610840 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.5129. Min Act: -0.0000

Data Index: 846822 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.5011. Min Act: -0.0000

Data Index: 1423768 (Python Code)

Max Activating Token Index: 486

Text #9

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.4550. Min Act: -0.0000

Data Index: 1483219 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1539055 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.4224. Min Act: -0.0000

Data Index: 1458061 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.4140. Min Act: -0.0000

Data Index: 1615860 (Python Code)

Max Activating Token Index: 541

Text #13

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1150371 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1417104 (Python Code)

Max Activating Token Index: 118

Text #15

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.3400. Min Act: -0.0000

Data Index: 1606174 (Python Code)

Max Activating Token Index: 439

Text #16

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.3361. Min Act: -0.0000

Data Index: 1471565 (Python Code)

Max Activating Token Index: 980

Text #17

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1656092 (Python Code)

Max Activating Token Index: 413

Text #18

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.2615. Min Act: -0.0000

Data Index: 1475314 (Python Code)

Max Activating Token Index: 837

Text #19

Max Range: 1.9484. Min Range: -1.9484

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1507983 (Python Code)

Max Activating Token Index: 450