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

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

Neuron 1267 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: 5.5737. Min Range: -5.5737

Max Act: 5.5737. Min Act: -0.1700

Data Index: 1412902 (Python Code)

Max Activating Token Index: 969

Text #1

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.5425. Min Act: -0.1700

Data Index: 1409516 (Python Code)

Max Activating Token Index: 317

Text #2

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.5737. Min Act: -0.1700

Data Index: 1567813 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.5425. Min Act: -0.1700

Data Index: 1515719 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.4175. Min Act: -0.1700

Data Index: 155911 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.4175. Min Act: -0.1700

Data Index: 143491 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.4175. Min Act: -0.1700

Data Index: 1472953 (Python Code)

Max Activating Token Index: 886

Text #7

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.4175. Min Act: -0.1700

Data Index: 1013090 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.3862. Min Act: -0.1700

Data Index: 529077 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.3237. Min Act: -0.1700

Data Index: 1488463 (Python Code)

Max Activating Token Index: 423

Text #10

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.3550. Min Act: -0.1700

Data Index: 1109835 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.2612. Min Act: -0.1700

Data Index: 778038 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.2925. Min Act: -0.1700

Data Index: 796736 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.2925. Min Act: -0.1700

Data Index: 1459151 (Python Code)

Max Activating Token Index: 763

Text #14

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.2612. Min Act: -0.1700

Data Index: 506291 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.2300. Min Act: -0.1700

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.3237. Min Act: -0.1700

Data Index: 380147 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.2612. Min Act: -0.1700

Data Index: 746118 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.2612. Min Act: -0.1700

Data Index: 471088 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 5.5737. Min Range: -5.5737

Max Act: 5.3237. Min Act: -0.1700

Data Index: 604092 (C4 (Web Text))

Max Activating Token Index: 606