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

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

Neuron 837 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.7441. Min Act: -0.1700

Data Index: 1279790 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.7128. Min Act: -0.1700

Data Index: 1548587 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1381289 (Python Code)

Max Activating Token Index: 108

Text #3

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6815. Min Act: -0.1700

Data Index: 1624155 (Python Code)

Max Activating Token Index: 126

Text #4

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6815. Min Act: -0.1700

Data Index: 1475940 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1484972 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6815. Min Act: -0.1700

Data Index: 1578632 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1451392 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6189. Min Act: -0.1700

Data Index: 1361362 (Python Code)

Max Activating Token Index: 57

Text #9

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6189. Min Act: -0.1700

Data Index: 1409787 (Python Code)

Max Activating Token Index: 624

Text #10

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1599715 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6189. Min Act: -0.1700

Data Index: 1412849 (Python Code)

Max Activating Token Index: 543

Text #12

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6189. Min Act: -0.1700

Data Index: 1403033 (Python Code)

Max Activating Token Index: 304

Text #13

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1533154 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1647725 (Python Code)

Max Activating Token Index: 458

Text #15

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.6189. Min Act: -0.1700

Data Index: 1641267 (Python Code)

Max Activating Token Index: 605

Text #16

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1595619 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1387403 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1523673 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 3.7441. Min Range: -3.7441

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1467782 (Python Code)

Max Activating Token Index: 989