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

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

Neuron 707 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2651. Min Act: -0.1700

Data Index: 267659 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1864. Min Act: -0.1700

Data Index: 658791 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2336. Min Act: -0.1700

Data Index: 1236481 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2336. Min Act: -0.1700

Data Index: 447248 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2336. Min Act: -0.1700

Data Index: 1211974 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1864. Min Act: -0.1700

Data Index: 163825 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.2179. Min Act: -0.1700

Data Index: 533779 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1707. Min Act: -0.1700

Data Index: 819180 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1550. Min Act: -0.1700

Data Index: 1322592 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1550. Min Act: -0.1700

Data Index: 713124 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1550. Min Act: -0.1700

Data Index: 188823 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1392. Min Act: -0.1700

Data Index: 238161 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1392. Min Act: -0.1700

Data Index: 335164 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1392. Min Act: -0.1700

Data Index: 1292911 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1234. Min Act: -0.1700

Data Index: 960812 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1234. Min Act: -0.1700

Data Index: 1090899 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1077. Min Act: -0.1700

Data Index: 597363 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.1234. Min Act: -0.1700

Data Index: 1051085 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.0919. Min Act: -0.1700

Data Index: 1293171 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.2651. Min Range: -3.2651

Max Act: 3.0919. Min Act: -0.1700

Data Index: 367193 (C4 (Web Text))

Max Activating Token Index: 951