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

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

Neuron 1976 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: 5.7362. Min Range: -5.7362

Max Act: 5.7362. Min Act: -0.1700

Data Index: 128318 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.7050. Min Act: -0.1700

Data Index: 615710 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.5175. Min Act: -0.1700

Data Index: 855772 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.5175. Min Act: -0.1700

Data Index: 775518 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.4862. Min Act: -0.1700

Data Index: 1154059 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.5800. Min Act: -0.1700

Data Index: 1251429 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.5487. Min Act: -0.1700

Data Index: 798407 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.5487. Min Act: -0.1700

Data Index: 349964 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.5175. Min Act: -0.1700

Data Index: 493781 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.5175. Min Act: -0.1700

Data Index: 444764 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.3925. Min Act: -0.1700

Data Index: 803586 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.4862. Min Act: -0.1700

Data Index: 1085028 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.4237. Min Act: -0.1700

Data Index: 1007301 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.4550. Min Act: -0.1700

Data Index: 935413 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.5487. Min Act: -0.1700

Data Index: 25645 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.4237. Min Act: -0.1700

Data Index: 630391 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.4237. Min Act: -0.1700

Data Index: 1140818 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.4550. Min Act: -0.1700

Data Index: 1126729 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.4237. Min Act: -0.1700

Data Index: 494767 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 5.7362. Min Range: -5.7362

Max Act: 5.3925. Min Act: -0.1700

Data Index: 935839 (C4 (Web Text))

Max Activating Token Index: 142