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

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

Neuron 1676 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: 4.0361. Min Range: -4.0361

Max Act: 4.0361. Min Act: -0.1700

Data Index: 984271 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 4.0361. Min Range: -4.0361

Max Act: 4.0168. Min Act: -0.1700

Data Index: 1035309 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 4.0361. Min Range: -4.0361

Max Act: 4.0125. Min Act: -0.1700

Data Index: 720387 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9859. Min Act: -0.1700

Data Index: 1285252 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9872. Min Act: -0.1700

Data Index: 285101 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9769. Min Act: -0.1700

Data Index: 201734 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9649. Min Act: -0.1700

Data Index: 440101 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9609. Min Act: -0.1700

Data Index: 545308 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9536. Min Act: -0.1700

Data Index: 294863 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9277. Min Act: -0.1700

Data Index: 1123272 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9401. Min Act: -0.1700

Data Index: 973013 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9108. Min Act: -0.1700

Data Index: 1142647 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.9246. Min Act: -0.1700

Data Index: 1287180 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8602. Min Act: -0.1700

Data Index: 1111700 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8613. Min Act: -0.1700

Data Index: 248213 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8560. Min Act: -0.1700

Data Index: 1240030 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8564. Min Act: -0.1700

Data Index: 755247 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8632. Min Act: -0.1700

Data Index: 1316797 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8500. Min Act: -0.1700

Data Index: 1281277 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 4.0361. Min Range: -4.0361

Max Act: 3.8312. Min Act: -0.1700

Data Index: 1070187 (C4 (Web Text))

Max Activating Token Index: 242