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

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

Neuron 625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.3882. Min Act: -0.1700

Data Index: 824007 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.3882. Min Act: -0.1700

Data Index: 338519 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.2944. Min Act: -0.1700

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.2944. Min Act: -0.1700

Data Index: 1351333 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.1694. Min Act: -0.1700

Data Index: 450677 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.2007. Min Act: -0.1700

Data Index: 996363 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.2319. Min Act: -0.1700

Data Index: 583817 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.2319. Min Act: -0.1700

Data Index: 610273 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.1069. Min Act: -0.1700

Data Index: 988629 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.1694. Min Act: -0.1700

Data Index: 1200847 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.0444. Min Act: -0.1700

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.0444. Min Act: -0.1700

Data Index: 796233 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.0757. Min Act: -0.1700

Data Index: 869863 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.0132. Min Act: -0.1700

Data Index: 607177 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.0757. Min Act: -0.1700

Data Index: 1194416 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 5.3882. Min Range: -5.3882

Max Act: 4.9819. Min Act: -0.1700

Data Index: 869380 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.0132. Min Act: -0.1700

Data Index: 771791 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.0444. Min Act: -0.1700

Data Index: 1291107 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 5.3882. Min Range: -5.3882

Max Act: 4.9819. Min Act: -0.1700

Data Index: 808554 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 5.3882. Min Range: -5.3882

Max Act: 5.0444. Min Act: -0.1700

Data Index: 969165 (C4 (Web Text))

Max Activating Token Index: 39