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

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

Neuron 1904 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.3117. Min Act: -0.1700

Data Index: 297456 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.2648. Min Act: -0.1700

Data Index: 129426 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.2335. Min Act: -0.1699

Data Index: 1178921 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.2804. Min Act: -0.1700

Data Index: 705017 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.1867. Min Act: -0.1700

Data Index: 257026 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.1554. Min Act: -0.1700

Data Index: 1025453 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.1867. Min Act: -0.1700

Data Index: 171876 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.1867. Min Act: -0.1700

Data Index: 22705 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.1398. Min Act: -0.1700

Data Index: 713139 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.1554. Min Act: -0.1700

Data Index: 1328345 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.1398. Min Act: -0.1700

Data Index: 870754 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0929. Min Act: -0.1700

Data Index: 252545 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0929. Min Act: -0.1700

Data Index: 498227 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0773. Min Act: -0.1700

Data Index: 664783 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0773. Min Act: -0.1700

Data Index: 1200936 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0773. Min Act: -0.1700

Data Index: 450161 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0929. Min Act: -0.1700

Data Index: 398281 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0460. Min Act: -0.1700

Data Index: 417499 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0617. Min Act: -0.1700

Data Index: 593228 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 5.3117. Min Range: -5.3117

Max Act: 5.0460. Min Act: -0.1700

Data Index: 316797 (C4 (Web Text))

Max Activating Token Index: 710