Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1846 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.3718. Min Act: -0.1700

Data Index: 1639264 (Python Code)

Max Activating Token Index: 263

Text #1

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.2468. Min Act: -0.1700

Data Index: 1384409 (Python Code)

Max Activating Token Index: 679

Text #2

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.1218. Min Act: -0.1700

Data Index: 1622109 (Python Code)

Max Activating Token Index: 502

Text #3

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.1531. Min Act: -0.1700

Data Index: 1494657 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.1218. Min Act: -0.1700

Data Index: 1569374 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.0593. Min Act: -0.1700

Data Index: 1466798 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.1531. Min Act: -0.1700

Data Index: 1583486 (Python Code)

Max Activating Token Index: 405

Text #7

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.0281. Min Act: -0.1700

Data Index: 1387006 (Python Code)

Max Activating Token Index: 202

Text #8

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9968. Min Act: -0.1700

Data Index: 1420277 (Python Code)

Max Activating Token Index: 749

Text #9

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9656. Min Act: -0.1700

Data Index: 1653836 (Python Code)

Max Activating Token Index: 770

Text #10

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9968. Min Act: -0.1700

Data Index: 1560411 (Python Code)

Max Activating Token Index: 365

Text #11

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.0281. Min Act: -0.1700

Data Index: 1590208 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9656. Min Act: -0.1700

Data Index: 1468407 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9968. Min Act: -0.1700

Data Index: 1523050 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.0593. Min Act: -0.1700

Data Index: 1378032 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9968. Min Act: -0.1700

Data Index: 1576639 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 5.3718. Min Range: -5.3718

Max Act: 5.0281. Min Act: -0.1700

Data Index: 1384043 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9968. Min Act: -0.1700

Data Index: 1462735 (Python Code)

Max Activating Token Index: 96

Text #18

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9968. Min Act: -0.1700

Data Index: 1395830 (Python Code)

Max Activating Token Index: 379

Text #19

Max Range: 5.3718. Min Range: -5.3718

Max Act: 4.9343. Min Act: -0.1700

Data Index: 1534279 (Python Code)

Max Activating Token Index: 641