Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 818 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.7136. Min Act: -0.1700

Data Index: 1615448 (Python Code)

Max Activating Token Index: 460

Text #1

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.6497. Min Act: -0.1700

Data Index: 1477436 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.6126. Min Act: -0.1700

Data Index: 1377087 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.6327. Min Act: -0.1700

Data Index: 1419605 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.6281. Min Act: -0.1700

Data Index: 1418110 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.6256. Min Act: -0.1700

Data Index: 1464305 (Python Code)

Max Activating Token Index: 887

Text #6

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.5954. Min Act: -0.1700

Data Index: 1531986 (Python Code)

Max Activating Token Index: 657

Text #7

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.5617. Min Act: -0.1700

Data Index: 1498137 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.5232. Min Act: -0.1700

Data Index: 1522942 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.5487. Min Act: -0.1700

Data Index: 1623570 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.4863. Min Act: -0.1700

Data Index: 1418095 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.5126. Min Act: -0.1700

Data Index: 1424650 (Python Code)

Max Activating Token Index: 891

Text #12

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.4722. Min Act: -0.1700

Data Index: 1480342 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.4958. Min Act: -0.1700

Data Index: 1422000 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.4699. Min Act: -0.1700

Data Index: 1360277 (Python Code)

Max Activating Token Index: 603

Text #15

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.4572. Min Act: -0.1700

Data Index: 1508369 (Python Code)

Max Activating Token Index: 11

Text #16

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.4030. Min Act: -0.1700

Data Index: 1630627 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.3813. Min Act: -0.1700

Data Index: 1449776 (Python Code)

Max Activating Token Index: 536

Text #18

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.4156. Min Act: -0.1700

Data Index: 1460659 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 6.7136. Min Range: -6.7136

Max Act: 6.3698. Min Act: -0.1700

Data Index: 1507915 (Python Code)

Max Activating Token Index: 356