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

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

Neuron 862 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.3643. Min Act: -0.1700

Data Index: 811993 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.3643. Min Act: -0.1700

Data Index: 1002797 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.3643. Min Act: -0.1700

Data Index: 79420 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.3018. Min Act: -0.1700

Data Index: 405716 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2706. Min Act: -0.1700

Data Index: 250859 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2393. Min Act: -0.1700

Data Index: 165786 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.2081. Min Act: -0.1700

Data Index: 586184 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1768. Min Act: -0.1700

Data Index: 657280 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.0831. Min Act: -0.1699

Data Index: 678327 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.1143. Min Act: -0.1700

Data Index: 601498 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.0831. Min Act: -0.1700

Data Index: 1225226 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.0831. Min Act: -0.1700

Data Index: 48167 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.0831. Min Act: -0.1700

Data Index: 167070 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.0206. Min Act: -0.1700

Data Index: 1260491 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 5.3643. Min Range: -5.3643

Max Act: 5.0518. Min Act: -0.1700

Data Index: 342066 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 5.3643. Min Range: -5.3643

Max Act: 4.9581. Min Act: -0.1700

Data Index: 962916 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 5.3643. Min Range: -5.3643

Max Act: 4.9581. Min Act: -0.1700

Data Index: 5798 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 5.3643. Min Range: -5.3643

Max Act: 4.9581. Min Act: -0.1700

Data Index: 1074415 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 5.3643. Min Range: -5.3643

Max Act: 4.9893. Min Act: -0.1700

Data Index: 1094328 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 5.3643. Min Range: -5.3643

Max Act: 4.8956. Min Act: -0.1700

Data Index: 1002143 (C4 (Web Text))

Max Activating Token Index: 940