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

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

Neuron 3365 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: 1.1292. Min Range: -1.1292

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1518062 (Python Code)

Max Activating Token Index: 556

Text #1

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1655691 (Python Code)

Max Activating Token Index: 488

Text #2

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1515757 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0402. Min Act: -0.0000

Data Index: 1581963 (Python Code)

Max Activating Token Index: 499

Text #4

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0384. Min Act: 0.0000

Data Index: 1469471 (Python Code)

Max Activating Token Index: 602

Text #5

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1439822 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 1.1292. Min Range: -1.1292

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1388720 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1558792 (Python Code)

Max Activating Token Index: 548

Text #8

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1610399 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8987. Min Act: -0.0000

Data Index: 1583817 (Python Code)

Max Activating Token Index: 150

Text #10

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1363841 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1621112 (Python Code)

Max Activating Token Index: 579

Text #12

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1525475 (Python Code)

Max Activating Token Index: 325

Text #13

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1560996 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1559963 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1601035 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8448. Min Act: 0.0000

Data Index: 1519131 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1448781 (Python Code)

Max Activating Token Index: 559

Text #18

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1531182 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 1.1292. Min Range: -1.1292

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1467142 (Python Code)

Max Activating Token Index: 46