Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1863 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.1037. Min Act: -0.1700

Data Index: 80173 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.1037. Min Act: -0.1700

Data Index: 1095370 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0099. Min Act: -0.1700

Data Index: 550023 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0724. Min Act: -0.1700

Data Index: 964072 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0412. Min Act: -0.1700

Data Index: 77292 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0412. Min Act: -0.1700

Data Index: 996111 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.9474. Min Act: -0.1700

Data Index: 680125 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0412. Min Act: -0.1700

Data Index: 239014 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0412. Min Act: -0.1700

Data Index: 1032192 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.1037. Min Act: -0.1700

Data Index: 1243198 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0412. Min Act: -0.1700

Data Index: 509562 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.9787. Min Act: -0.1700

Data Index: 1046837 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0724. Min Act: -0.1700

Data Index: 747097 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0099. Min Act: -0.1700

Data Index: 1204165 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0099. Min Act: -0.1700

Data Index: 285219 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.9787. Min Act: -0.1700

Data Index: 1082178 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 5.1037. Min Range: -5.1037

Max Act: 4.9787. Min Act: -0.1700

Data Index: 635354 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0412. Min Act: -0.1700

Data Index: 469159 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0099. Min Act: -0.1700

Data Index: 424215 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 5.1037. Min Range: -5.1037

Max Act: 5.0099. Min Act: -0.1700

Data Index: 1080977 (C4 (Web Text))

Max Activating Token Index: 343