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

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

Neuron 1876 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: 5.1841. Min Range: -5.1841

Max Act: 5.1841. Min Act: -0.1700

Data Index: 1161555 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 5.1841. Min Range: -5.1841

Max Act: 5.1841. Min Act: -0.1700

Data Index: 1020006 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 5.1841. Min Range: -5.1841

Max Act: 5.1216. Min Act: -0.1700

Data Index: 819949 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 5.1841. Min Range: -5.1841

Max Act: 5.0903. Min Act: -0.1700

Data Index: 1016181 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.9653. Min Act: -0.1700

Data Index: 593424 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.9341. Min Act: -0.1700

Data Index: 1298186 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.9028. Min Act: -0.1700

Data Index: 512048 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8403. Min Act: -0.1700

Data Index: 562580 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8403. Min Act: -0.1700

Data Index: 1173830 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8716. Min Act: -0.1700

Data Index: 158262 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8403. Min Act: -0.1700

Data Index: 1328198 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8403. Min Act: -0.1700

Data Index: 952649 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8403. Min Act: -0.1700

Data Index: 852690 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8091. Min Act: -0.1700

Data Index: 287747 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8091. Min Act: -0.1700

Data Index: 694320 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8091. Min Act: -0.1700

Data Index: 1269286 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.8403. Min Act: -0.1700

Data Index: 1021710 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.7466. Min Act: -0.1700

Data Index: 881620 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.7778. Min Act: -0.1700

Data Index: 1246779 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 5.1841. Min Range: -5.1841

Max Act: 4.7778. Min Act: -0.1700

Data Index: 475823 (C4 (Web Text))

Max Activating Token Index: 772