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

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

Neuron 1267 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: 3.9268. Min Range: -3.9268

Max Act: 3.9268. Min Act: -0.1700

Data Index: 290166 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.7705. Min Act: -0.1700

Data Index: 931384 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.6453. Min Act: -0.1699

Data Index: 560061 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.6453. Min Act: -0.1700

Data Index: 781849 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.6766. Min Act: -0.1700

Data Index: 441187 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.5357. Min Act: -0.1700

Data Index: 1336950 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.5357. Min Act: -0.1700

Data Index: 1013738 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.5357. Min Act: -0.1698

Data Index: 951761 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.5200. Min Act: -0.1700

Data Index: 311050 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.5043. Min Act: -0.1700

Data Index: 260223 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.5200. Min Act: -0.1700

Data Index: 698873 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.4730. Min Act: -0.1700

Data Index: 271639 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.5043. Min Act: -0.1700

Data Index: 89656 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.4730. Min Act: -0.1700

Data Index: 356242 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.4260. Min Act: -0.1700

Data Index: 700315 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.4260. Min Act: -0.1700

Data Index: 967086 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.4260. Min Act: -0.1700

Data Index: 113313 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.4260. Min Act: -0.1700

Data Index: 463304 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.4260. Min Act: -0.1700

Data Index: 1265205 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 3.9268. Min Range: -3.9268

Max Act: 3.4103. Min Act: -0.1700

Data Index: 986857 (C4 (Web Text))

Max Activating Token Index: 373