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

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

Neuron 49 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: 4.0360. Min Range: -4.0360

Max Act: 4.0360. Min Act: -0.1700

Data Index: 1129924 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 4.0360. Min Range: -4.0360

Max Act: 4.0145. Min Act: -0.1700

Data Index: 1005276 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.9215. Min Act: -0.1700

Data Index: 287165 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.8795. Min Act: -0.1700

Data Index: 600187 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7915. Min Act: -0.1700

Data Index: 1571183 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7950. Min Act: -0.1700

Data Index: 231566 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7842. Min Act: -0.1700

Data Index: 505801 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7821. Min Act: -0.1700

Data Index: 656911 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7603. Min Act: -0.1700

Data Index: 238782 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7461. Min Act: -0.1700

Data Index: 708701 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7453. Min Act: -0.1700

Data Index: 1654732 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7267. Min Act: -0.1700

Data Index: 1172397 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7400. Min Act: -0.1700

Data Index: 1230099 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7422. Min Act: -0.1700

Data Index: 384478 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7160. Min Act: -0.1700

Data Index: 1490187 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.7085. Min Act: -0.1700

Data Index: 432261 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.6832. Min Act: -0.1700

Data Index: 747629 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.6869. Min Act: -0.1700

Data Index: 317233 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.6785. Min Act: -0.1700

Data Index: 1258977 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 4.0360. Min Range: -4.0360

Max Act: 3.6870. Min Act: -0.1700

Data Index: 1088194 (C4 (Web Text))

Max Activating Token Index: 213