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

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

Neuron 5852 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.7140. Min Act: -0.0000

Data Index: 1579243 (Python Code)

Max Activating Token Index: 456

Text #1

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.5809. Min Act: 0.0000

Data Index: 1565696 (Python Code)

Max Activating Token Index: 474

Text #2

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.6168. Min Act: -0.0000

Data Index: 575679 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1429617 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4053. Min Act: -0.0000

Data Index: 1612556 (Python Code)

Max Activating Token Index: 615

Text #5

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.4403. Min Act: -0.0000

Data Index: 1380027 (Python Code)

Max Activating Token Index: 535

Text #6

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3807. Min Act: -0.0000

Data Index: 1451526 (Python Code)

Max Activating Token Index: 424

Text #7

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3451. Min Act: -0.0000

Data Index: 1423440 (Python Code)

Max Activating Token Index: 524

Text #8

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2678. Min Act: -0.0000

Data Index: 1548041 (Python Code)

Max Activating Token Index: 297

Text #9

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1474410 (Python Code)

Max Activating Token Index: 906

Text #10

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1490166 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1583806 (Python Code)

Max Activating Token Index: 415

Text #12

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1376. Min Act: -0.0000

Data Index: 233750 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1392873 (Python Code)

Max Activating Token Index: 489

Text #14

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1480475 (Python Code)

Max Activating Token Index: 998

Text #15

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1468621 (Python Code)

Max Activating Token Index: 450

Text #16

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1734. Min Act: -0.0000

Data Index: 1550812 (Python Code)

Max Activating Token Index: 931

Text #17

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1422601 (Python Code)

Max Activating Token Index: 387

Text #18

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1543820 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1149. Min Act: -0.0000

Data Index: 1487938 (Python Code)

Max Activating Token Index: 338