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

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

Neuron 1969 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4154. Min Range: -3.4154

Max Act: 3.4154. Min Act: -0.1700

Data Index: 997404 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 3.4154. Min Range: -3.4154

Max Act: 3.1955. Min Act: -0.1700

Data Index: 838236 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 3.4154. Min Range: -3.4154

Max Act: 3.1798. Min Act: -0.1700

Data Index: 1068301 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 3.4154. Min Range: -3.4154

Max Act: 3.1483. Min Act: -0.1700

Data Index: 163698 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 3.4154. Min Range: -3.4154

Max Act: 3.1168. Min Act: -0.1700

Data Index: 1299801 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 3.4154. Min Range: -3.4154

Max Act: 3.0537. Min Act: -0.1700

Data Index: 895708 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 3.4154. Min Range: -3.4154

Max Act: 3.0063. Min Act: -0.1700

Data Index: 1309250 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 3.4154. Min Range: -3.4154

Max Act: 3.0221. Min Act: -0.1700

Data Index: 664839 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9905. Min Act: -0.1700

Data Index: 301674 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9905. Min Act: -0.1700

Data Index: 468090 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9746. Min Act: -0.1700

Data Index: 1195653 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9905. Min Act: -0.1700

Data Index: 642576 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9588. Min Act: -0.1700

Data Index: 431423 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9271. Min Act: -0.1700

Data Index: 527968 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9271. Min Act: -0.1700

Data Index: 1039587 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9430. Min Act: -0.1700

Data Index: 797247 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9430. Min Act: -0.1700

Data Index: 607326 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9113. Min Act: -0.1700

Data Index: 513116 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.8796. Min Act: -0.1700

Data Index: 329370 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 3.4154. Min Range: -3.4154

Max Act: 2.9113. Min Act: -0.1700

Data Index: 1051444 (C4 (Web Text))

Max Activating Token Index: 252