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

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

Neuron 275 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: 5.7019. Min Range: -5.7019

Max Act: 5.7019. Min Act: -0.1700

Data Index: 1165686 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.5769. Min Act: -0.1700

Data Index: 416420 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.5144. Min Act: -0.1700

Data Index: 48081 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.5144. Min Act: -0.1700

Data Index: 1258133 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.5144. Min Act: -0.1700

Data Index: 245529 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3894. Min Act: -0.1700

Data Index: 926349 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3894. Min Act: -0.1700

Data Index: 227010 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.4206. Min Act: -0.1700

Data Index: 252494 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3581. Min Act: -0.1700

Data Index: 740635 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.4206. Min Act: -0.1700

Data Index: 1042053 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2644. Min Act: -0.1700

Data Index: 435150 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3269. Min Act: -0.1700

Data Index: 223262 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2644. Min Act: -0.1700

Data Index: 893115 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2956. Min Act: -0.1700

Data Index: 70696 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2956. Min Act: -0.1700

Data Index: 1260877 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2019. Min Act: -0.1700

Data Index: 217009 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.3269. Min Act: -0.1700

Data Index: 413158 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2644. Min Act: -0.1700

Data Index: 1242082 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2019. Min Act: -0.1700

Data Index: 1285021 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 5.7019. Min Range: -5.7019

Max Act: 5.2644. Min Act: -0.1700

Data Index: 861542 (C4 (Web Text))

Max Activating Token Index: 46