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

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

Neuron 1036 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: 5.7622. Min Range: -5.7622

Max Act: 5.7622. Min Act: -0.1700

Data Index: 838043 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.7309. Min Act: -0.1700

Data Index: 32621 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.7309. Min Act: -0.1700

Data Index: 683471 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.6372. Min Act: -0.1700

Data Index: 880008 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.6059. Min Act: -0.1700

Data Index: 1215347 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.6059. Min Act: -0.1700

Data Index: 856616 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.5434. Min Act: -0.1700

Data Index: 1026412 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.5434. Min Act: -0.1700

Data Index: 396274 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.5434. Min Act: -0.1700

Data Index: 212246 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.5122. Min Act: -0.1700

Data Index: 842694 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.4809. Min Act: -0.1700

Data Index: 664008 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.5434. Min Act: -0.1700

Data Index: 413628 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.4809. Min Act: -0.1700

Data Index: 130691 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.4497. Min Act: -0.1700

Data Index: 284382 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.3872. Min Act: -0.1700

Data Index: 1084863 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.4497. Min Act: -0.1700

Data Index: 1210309 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.4184. Min Act: -0.1700

Data Index: 1276177 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.4497. Min Act: -0.1700

Data Index: 454160 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.3872. Min Act: -0.1700

Data Index: 1046398 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 5.7622. Min Range: -5.7622

Max Act: 5.4184. Min Act: -0.1700

Data Index: 1203359 (C4 (Web Text))

Max Activating Token Index: 734