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

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

Neuron 4268 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: 2.7539. Min Range: -2.7539

Max Act: 2.7539. Min Act: -0.0000

Data Index: 1594770 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.7334. Min Act: -0.0000

Data Index: 1509824 (Python Code)

Max Activating Token Index: 1010

Text #2

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.4917. Min Act: -0.0000

Data Index: 1558891 (Python Code)

Max Activating Token Index: 78

Text #3

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.4590. Min Act: -0.0000

Data Index: 1436821 (Python Code)

Max Activating Token Index: 79

Text #4

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.3930. Min Act: -0.0000

Data Index: 1419813 (Python Code)

Max Activating Token Index: 236

Text #5

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.1478. Min Act: -0.0000

Data Index: 1402890 (Python Code)

Max Activating Token Index: 521

Text #6

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.1462. Min Act: -0.0000

Data Index: 1478564 (Python Code)

Max Activating Token Index: 978

Text #7

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.2145. Min Act: -0.0000

Data Index: 1458093 (Python Code)

Max Activating Token Index: 956

Text #8

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0316. Min Act: -0.0000

Data Index: 1399629 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.9960. Min Act: -0.0000

Data Index: 1526700 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.8605. Min Act: -0.0000

Data Index: 1575548 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0345. Min Act: -0.0000

Data Index: 1452756 (Python Code)

Max Activating Token Index: 859

Text #12

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0166. Min Act: -0.0000

Data Index: 1379221 (Python Code)

Max Activating Token Index: 857

Text #13

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.8011. Min Act: -0.0000

Data Index: 1456743 (Python Code)

Max Activating Token Index: 348

Text #14

Max Range: 2.7539. Min Range: -2.7539

Max Act: 2.0189. Min Act: -0.0000

Data Index: 1450388 (Python Code)

Max Activating Token Index: 575

Text #15

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.6630. Min Act: -0.0000

Data Index: 1481169 (Python Code)

Max Activating Token Index: 803

Text #16

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.7752. Min Act: -0.0000

Data Index: 1537556 (Python Code)

Max Activating Token Index: 875

Text #17

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.7641. Min Act: -0.0000

Data Index: 1578512 (Python Code)

Max Activating Token Index: 851

Text #18

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.7499. Min Act: -0.0000

Data Index: 1596968 (Python Code)

Max Activating Token Index: 372

Text #19

Max Range: 2.7539. Min Range: -2.7539

Max Act: 1.8489. Min Act: -0.0000

Data Index: 1414359 (Python Code)

Max Activating Token Index: 845