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

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

Neuron 524 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: 5.7141. Min Range: -5.7141

Max Act: 5.7141. Min Act: -0.1700

Data Index: 269225 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.5891. Min Act: -0.1700

Data Index: 546166 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.5578. Min Act: -0.1700

Data Index: 465797 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.4328. Min Act: -0.1700

Data Index: 468294 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.3391. Min Act: -0.1700

Data Index: 1350793 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.2766. Min Act: -0.1700

Data Index: 883030 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.3078. Min Act: -0.1700

Data Index: 501797 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.3078. Min Act: -0.1700

Data Index: 661080 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.2766. Min Act: -0.1694

Data Index: 627037 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.2453. Min Act: -0.1700

Data Index: 272717 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.2141. Min Act: -0.1700

Data Index: 774891 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.2141. Min Act: -0.1700

Data Index: 606755 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.1828. Min Act: -0.1700

Data Index: 737656 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.1828. Min Act: -0.1700

Data Index: 253613 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.2141. Min Act: -0.1700

Data Index: 1355202 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.1516. Min Act: -0.1700

Data Index: 426977 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.1516. Min Act: -0.1700

Data Index: 757366 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.0891. Min Act: -0.1700

Data Index: 948887 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.0891. Min Act: -0.1700

Data Index: 612264 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 5.7141. Min Range: -5.7141

Max Act: 5.1203. Min Act: -0.1700

Data Index: 1243923 (C4 (Web Text))

Max Activating Token Index: 819