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

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

Neuron 1517 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9941. Min Act: -0.1700

Data Index: 1558396 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9772. Min Act: -0.1700

Data Index: 1362931 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9603. Min Act: -0.1700

Data Index: 1564446 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9433. Min Act: -0.1700

Data Index: 1633340 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9263. Min Act: -0.1700

Data Index: 1456130 (Python Code)

Max Activating Token Index: 271

Text #5

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9263. Min Act: -0.1700

Data Index: 1501491 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9263. Min Act: -0.1700

Data Index: 1402443 (Python Code)

Max Activating Token Index: 247

Text #7

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9263. Min Act: -0.1700

Data Index: 1609202 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9093. Min Act: -0.1700

Data Index: 1442034 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9093. Min Act: -0.1700

Data Index: 1448403 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9263. Min Act: -0.1699

Data Index: 1611846 (Python Code)

Max Activating Token Index: 660

Text #11

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9093. Min Act: -0.1700

Data Index: 1410241 (Python Code)

Max Activating Token Index: 822

Text #12

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9263. Min Act: -0.1700

Data Index: 1416325 (Python Code)

Max Activating Token Index: 813

Text #13

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.9008. Min Act: -0.1700

Data Index: 1366199 (Python Code)

Max Activating Token Index: 318

Text #14

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8752. Min Act: -0.1700

Data Index: 1489884 (Python Code)

Max Activating Token Index: 412

Text #15

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8923. Min Act: -0.1700

Data Index: 1540347 (Python Code)

Max Activating Token Index: 545

Text #16

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8837. Min Act: -0.1700

Data Index: 105225 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8837. Min Act: -0.1700

Data Index: 1420674 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8837. Min Act: -0.1700

Data Index: 1460399 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 1.9941. Min Range: -1.9941

Max Act: 1.8837. Min Act: -0.1700

Data Index: 889382 (C4 (Web Text))

Max Activating Token Index: 788