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

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

Neuron 1113 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1676. Min Range: -3.1676

Max Act: 3.1676. Min Act: -0.1700

Data Index: 936462 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.1676. Min Range: -3.1676

Max Act: 3.0573. Min Act: -0.1700

Data Index: 989527 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.1676. Min Range: -3.1676

Max Act: 3.0415. Min Act: -0.1700

Data Index: 1306464 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 3.1676. Min Range: -3.1676

Max Act: 3.0257. Min Act: -0.1700

Data Index: 1026512 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9941. Min Act: -0.1700

Data Index: 878297 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 3.1676. Min Range: -3.1676

Max Act: 3.0099. Min Act: -0.1700

Data Index: 360683 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9941. Min Act: -0.1700

Data Index: 648219 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9783. Min Act: -0.1700

Data Index: 556246 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9783. Min Act: -0.1700

Data Index: 407271 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 3.1676. Min Range: -3.1676

Max Act: 3.0099. Min Act: -0.1700

Data Index: 197709 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9941. Min Act: -0.1700

Data Index: 617659 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9783. Min Act: -0.1700

Data Index: 825291 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9624. Min Act: -0.1700

Data Index: 1344625 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9941. Min Act: -0.1700

Data Index: 336498 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9941. Min Act: -0.1700

Data Index: 840143 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9624. Min Act: -0.1700

Data Index: 1191456 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9624. Min Act: -0.1700

Data Index: 297203 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9308. Min Act: -0.1700

Data Index: 645933 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9624. Min Act: -0.1700

Data Index: 614152 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 3.1676. Min Range: -3.1676

Max Act: 2.9466. Min Act: -0.1700

Data Index: 1068809 (C4 (Web Text))

Max Activating Token Index: 802