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

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

Neuron 1408 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: 5.7299. Min Range: -5.7299

Max Act: 5.6987. Min Act: -0.1700

Data Index: 901071 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6987. Min Act: -0.1700

Data Index: 856652 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6362. Min Act: -0.1700

Data Index: 562497 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.7299. Min Act: -0.1700

Data Index: 521032 (C4 (Web Text))

Max Activating Token Index: 260

Text #4

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6987. Min Act: -0.1700

Data Index: 1248145 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6049. Min Act: -0.1700

Data Index: 623778 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6049. Min Act: -0.1700

Data Index: 1203656 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6049. Min Act: -0.1700

Data Index: 1103364 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6049. Min Act: -0.1700

Data Index: 542674 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.6049. Min Act: -0.1700

Data Index: 742258 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.5737. Min Act: -0.1700

Data Index: 569435 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.5737. Min Act: -0.1700

Data Index: 1286385 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.5737. Min Act: -0.1700

Data Index: 61899 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.5424. Min Act: -0.1700

Data Index: 728932 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.5112. Min Act: -0.1700

Data Index: 1238357 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.4174. Min Act: -0.1700

Data Index: 378791 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.4799. Min Act: -0.1700

Data Index: 724710 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.4799. Min Act: -0.1700

Data Index: 292381 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.4487. Min Act: -0.1700

Data Index: 1067390 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 5.7299. Min Range: -5.7299

Max Act: 5.4799. Min Act: -0.1700

Data Index: 374024 (C4 (Web Text))

Max Activating Token Index: 542