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

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

Neuron 3249 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.9374. Min Act: -0.0000

Data Index: 1446722 (Python Code)

Max Activating Token Index: 599

Text #1

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1649297 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1400946 (Python Code)

Max Activating Token Index: 417

Text #3

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1499149 (Python Code)

Max Activating Token Index: 698

Text #4

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7459. Min Act: -0.0000

Data Index: 1594201 (Python Code)

Max Activating Token Index: 518

Text #5

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1485766 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7368. Min Act: -0.0000

Data Index: 1517300 (Python Code)

Max Activating Token Index: 234

Text #7

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1601744 (Python Code)

Max Activating Token Index: 750

Text #8

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1550500 (Python Code)

Max Activating Token Index: 701

Text #9

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1371194 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1407552 (Python Code)

Max Activating Token Index: 993

Text #11

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1373468 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1628756 (Python Code)

Max Activating Token Index: 65

Text #13

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1388897 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6623. Min Act: 0.0000

Data Index: 1475063 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6288. Min Act: -0.0000

Data Index: 1468159 (Python Code)

Max Activating Token Index: 130

Text #16

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1595061 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6179. Min Act: 0.0000

Data Index: 1645654 (Python Code)

Max Activating Token Index: 385

Text #18

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1383681 (Python Code)

Max Activating Token Index: 142

Text #19

Max Range: 0.9374. Min Range: -0.9374

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1543986 (Python Code)

Max Activating Token Index: 339