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

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

Neuron 1958 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: 3.9214. Min Range: -3.9214

Max Act: 3.8901. Min Act: -0.1700

Data Index: 1587333 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.9214. Min Act: -0.1700

Data Index: 1421464 (Python Code)

Max Activating Token Index: 759

Text #2

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.7806. Min Act: -0.1700

Data Index: 1442913 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.7024. Min Act: -0.1700

Data Index: 1405929 (Python Code)

Max Activating Token Index: 210

Text #4

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.6867. Min Act: -0.1700

Data Index: 1489566 (Python Code)

Max Activating Token Index: 576

Text #5

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.6711. Min Act: -0.1700

Data Index: 1540680 (Python Code)

Max Activating Token Index: 284

Text #6

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.6554. Min Act: -0.1700

Data Index: 1440046 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.6867. Min Act: -0.1700

Data Index: 1420273 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.5928. Min Act: -0.1700

Data Index: 787194 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.6241. Min Act: -0.1700

Data Index: 909758 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.6398. Min Act: -0.1700

Data Index: 1428581 (Python Code)

Max Activating Token Index: 902

Text #11

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.6085. Min Act: -0.1700

Data Index: 1028918 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.6085. Min Act: -0.1700

Data Index: 92895 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.5772. Min Act: -0.1700

Data Index: 1525784 (Python Code)

Max Activating Token Index: 664

Text #14

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.5772. Min Act: -0.1700

Data Index: 1365369 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.5928. Min Act: -0.1700

Data Index: 466172 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.5928. Min Act: -0.1700

Data Index: 383704 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.5928. Min Act: -0.1700

Data Index: 701994 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.5928. Min Act: -0.1700

Data Index: 673632 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 3.9214. Min Range: -3.9214

Max Act: 3.5458. Min Act: -0.1700

Data Index: 1077569 (C4 (Web Text))

Max Activating Token Index: 417