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

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

Neuron 2837 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: 2.2332. Min Range: -2.2332

Max Act: 2.2332. Min Act: -0.0000

Data Index: 1528715 (Python Code)

Max Activating Token Index: 332

Text #1

Max Range: 2.2332. Min Range: -2.2332

Max Act: 2.0615. Min Act: -0.0000

Data Index: 1622570 (Python Code)

Max Activating Token Index: 468

Text #2

Max Range: 2.2332. Min Range: -2.2332

Max Act: 1.8530. Min Act: -0.0000

Data Index: 1516169 (Python Code)

Max Activating Token Index: 182

Text #3

Max Range: 2.2332. Min Range: -2.2332

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1645760 (Python Code)

Max Activating Token Index: 545

Text #4

Max Range: 2.2332. Min Range: -2.2332

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1579937 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 2.2332. Min Range: -2.2332

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1488245 (Python Code)

Max Activating Token Index: 956

Text #6

Max Range: 2.2332. Min Range: -2.2332

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1399629 (Python Code)

Max Activating Token Index: 401

Text #7

Max Range: 2.2332. Min Range: -2.2332

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1596093 (Python Code)

Max Activating Token Index: 162

Text #8

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9930. Min Act: -0.0000

Data Index: 1509449 (Python Code)

Max Activating Token Index: 487

Text #9

Max Range: 2.2332. Min Range: -2.2332

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1545238 (Python Code)

Max Activating Token Index: 903

Text #10

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1455088 (Python Code)

Max Activating Token Index: 378

Text #11

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1365247 (Python Code)

Max Activating Token Index: 222

Text #12

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1480248 (Python Code)

Max Activating Token Index: 472

Text #13

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1598865 (Python Code)

Max Activating Token Index: 932

Text #14

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1529840 (Python Code)

Max Activating Token Index: 581

Text #15

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1501600 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1508218 (Python Code)

Max Activating Token Index: 512

Text #17

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1450211 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1409521 (Python Code)

Max Activating Token Index: 827

Text #19

Max Range: 2.2332. Min Range: -2.2332

Max Act: 0.8504. Min Act: -0.0000

Data Index: 1594944 (Python Code)

Max Activating Token Index: 601