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

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

Neuron 798 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.9978. Min Act: -0.1700

Data Index: 344295 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.9352. Min Act: -0.1700

Data Index: 1101235 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.9040. Min Act: -0.1700

Data Index: 628676 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7788. Min Act: -0.1700

Data Index: 404485 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7788. Min Act: -0.1700

Data Index: 726616 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.8101. Min Act: -0.1700

Data Index: 887569 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7788. Min Act: -0.1700

Data Index: 1212139 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.8101. Min Act: -0.1700

Data Index: 219484 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7788. Min Act: -0.1700

Data Index: 1358627 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7788. Min Act: -0.1700

Data Index: 754119 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7476. Min Act: -0.1700

Data Index: 727309 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7788. Min Act: -0.1700

Data Index: 1219348 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7476. Min Act: -0.1700

Data Index: 433009 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7476. Min Act: -0.1700

Data Index: 649518 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7476. Min Act: -0.1700

Data Index: 454574 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7788. Min Act: -0.1700

Data Index: 230089 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7476. Min Act: -0.1700

Data Index: 1053061 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.6850. Min Act: -0.1700

Data Index: 901066 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7476. Min Act: -0.1700

Data Index: 1003169 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 3.9978. Min Range: -3.9978

Max Act: 3.7476. Min Act: -0.1700

Data Index: 640939 (C4 (Web Text))

Max Activating Token Index: 661