Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 232 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.0112. Min Range: -3.0112

Max Act: 3.0112. Min Act: -0.1700

Data Index: 744753 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9796. Min Act: -0.1700

Data Index: 1338382 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9163. Min Act: -0.1700

Data Index: 774174 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.9321. Min Act: -0.1695

Data Index: 166225 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8845. Min Act: -0.1700

Data Index: 1240576 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8687. Min Act: -0.1700

Data Index: 784667 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8528. Min Act: -0.1700

Data Index: 132150 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8369. Min Act: -0.1700

Data Index: 1357109 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8051. Min Act: -0.1700

Data Index: 286377 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8051. Min Act: -0.1699

Data Index: 954392 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8051. Min Act: -0.1700

Data Index: 502278 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8051. Min Act: -0.1699

Data Index: 187820 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.7891. Min Act: -0.1700

Data Index: 548953 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8051. Min Act: -0.1700

Data Index: 1036639 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8210. Min Act: -0.1700

Data Index: 830644 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8051. Min Act: -0.1700

Data Index: 1171877 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.7891. Min Act: -0.1700

Data Index: 237927 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8210. Min Act: -0.1700

Data Index: 1068166 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.8051. Min Act: -0.1698

Data Index: 808597 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 3.0112. Min Range: -3.0112

Max Act: 2.7732. Min Act: -0.1700

Data Index: 208767 (C4 (Web Text))

Max Activating Token Index: 525