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

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

Neuron 1436 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: 3.8378. Min Range: -3.8378

Max Act: 3.8378. Min Act: -0.1700

Data Index: 358138 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.8378. Min Act: -0.1700

Data Index: 619958 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.8065. Min Act: -0.1700

Data Index: 1020491 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.8065. Min Act: -0.1700

Data Index: 209158 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.7752. Min Act: -0.1700

Data Index: 214113 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.7439. Min Act: -0.1700

Data Index: 822527 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.7439. Min Act: -0.1700

Data Index: 920177 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.7126. Min Act: -0.1700

Data Index: 935862 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.7126. Min Act: -0.1700

Data Index: 1172418 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6813. Min Act: -0.1700

Data Index: 801157 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6500. Min Act: -0.1700

Data Index: 916740 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6813. Min Act: -0.1700

Data Index: 880435 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6187. Min Act: -0.1700

Data Index: 652031 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6187. Min Act: -0.1700

Data Index: 377896 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6187. Min Act: -0.1700

Data Index: 40850 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6813. Min Act: -0.1700

Data Index: 628076 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6187. Min Act: -0.1700

Data Index: 156021 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6500. Min Act: -0.1700

Data Index: 127040 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6187. Min Act: -0.1700

Data Index: 96448 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 3.8378. Min Range: -3.8378

Max Act: 3.6500. Min Act: -0.1700

Data Index: 550336 (C4 (Web Text))

Max Activating Token Index: 703