Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1786 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.3896. Min Act: -0.1700

Data Index: 801387 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.3268. Min Act: -0.1700

Data Index: 1383717 (Python Code)

Max Activating Token Index: 433

Text #2

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2797. Min Act: -0.1700

Data Index: 1611715 (Python Code)

Max Activating Token Index: 337

Text #3

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2640. Min Act: -0.1700

Data Index: 1402976 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2326. Min Act: -0.1700

Data Index: 1540486 (Python Code)

Max Activating Token Index: 544

Text #5

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2640. Min Act: -0.1700

Data Index: 1558716 (Python Code)

Max Activating Token Index: 499

Text #6

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2483. Min Act: -0.1700

Data Index: 1566673 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2326. Min Act: -0.1700

Data Index: 1589510 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2640. Min Act: -0.1700

Data Index: 1468046 (Python Code)

Max Activating Token Index: 220

Text #9

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2483. Min Act: -0.1700

Data Index: 1391840 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2483. Min Act: -0.1700

Data Index: 1474209 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2640. Min Act: -0.1700

Data Index: 1429536 (Python Code)

Max Activating Token Index: 734

Text #12

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2168. Min Act: -0.1700

Data Index: 1427165 (Python Code)

Max Activating Token Index: 676

Text #13

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2326. Min Act: -0.1700

Data Index: 1528248 (Python Code)

Max Activating Token Index: 537

Text #14

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2326. Min Act: -0.1700

Data Index: 1409064 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2326. Min Act: -0.1700

Data Index: 1391533 (Python Code)

Max Activating Token Index: 847

Text #16

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2483. Min Act: -0.1700

Data Index: 1635682 (Python Code)

Max Activating Token Index: 483

Text #17

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2483. Min Act: -0.1700

Data Index: 1491368 (Python Code)

Max Activating Token Index: 141

Text #18

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2326. Min Act: -0.1700

Data Index: 1545652 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 3.3896. Min Range: -3.3896

Max Act: 3.2326. Min Act: -0.1700

Data Index: 1452625 (Python Code)

Max Activating Token Index: 480