Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 295 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.4317. Min Act: -0.1700

Data Index: 707314 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.3067. Min Act: -0.1700

Data Index: 1012368 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2755. Min Act: -0.1700

Data Index: 1497029 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2755. Min Act: -0.1700

Data Index: 1478494 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2442. Min Act: -0.1700

Data Index: 1416104 (Python Code)

Max Activating Token Index: 122

Text #5

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2442. Min Act: -0.1700

Data Index: 171705 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1505. Min Act: -0.1700

Data Index: 1640843 (Python Code)

Max Activating Token Index: 377

Text #7

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.2130. Min Act: -0.1700

Data Index: 605330 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1817. Min Act: -0.1700

Data Index: 1619504 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1505. Min Act: -0.1700

Data Index: 1569457 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1192. Min Act: -0.1700

Data Index: 1060566 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1192. Min Act: -0.1700

Data Index: 1400630 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1505. Min Act: -0.1700

Data Index: 1445321 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1192. Min Act: -0.1700

Data Index: 1411908 (Python Code)

Max Activating Token Index: 10

Text #14

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1192. Min Act: -0.1700

Data Index: 1547496 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.0567. Min Act: -0.1700

Data Index: 1487857 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.1192. Min Act: -0.1700

Data Index: 1421888 (Python Code)

Max Activating Token Index: 263

Text #17

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.0567. Min Act: -0.1700

Data Index: 1477716 (Python Code)

Max Activating Token Index: 14

Text #18

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.0255. Min Act: -0.1700

Data Index: 1495485 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 5.4317. Min Range: -5.4317

Max Act: 5.0567. Min Act: -0.1700

Data Index: 1371529 (Python Code)

Max Activating Token Index: 85