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

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

Neuron 1578 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: 3.7009. Min Range: -3.7009

Max Act: 3.7009. Min Act: -0.1663

Data Index: 460420 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.6696. Min Act: -0.1700

Data Index: 662296 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.6070. Min Act: -0.1699

Data Index: 1234552 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5757. Min Act: -0.1700

Data Index: 1242002 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5914. Min Act: -0.1700

Data Index: 382268 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.6070. Min Act: -0.1700

Data Index: 511599 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5757. Min Act: -0.1700

Data Index: 1046405 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5757. Min Act: -0.1700

Data Index: 1637292 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5444. Min Act: -0.1699

Data Index: 1044044 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5444. Min Act: -0.1700

Data Index: 287808 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5444. Min Act: -0.1696

Data Index: 279515 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5287. Min Act: -0.1700

Data Index: 1241259 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5287. Min Act: -0.1700

Data Index: 60659 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5287. Min Act: -0.1700

Data Index: 661253 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5130. Min Act: -0.1700

Data Index: 294672 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.4817. Min Act: -0.1700

Data Index: 601177 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5130. Min Act: -0.1700

Data Index: 1538389 (Python Code)

Max Activating Token Index: 708

Text #17

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.5130. Min Act: -0.1700

Data Index: 1512155 (Python Code)

Max Activating Token Index: 867

Text #18

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.4817. Min Act: -0.1676

Data Index: 1599228 (Python Code)

Max Activating Token Index: 896

Text #19

Max Range: 3.7009. Min Range: -3.7009

Max Act: 3.4974. Min Act: -0.1700

Data Index: 1558825 (Python Code)

Max Activating Token Index: 471