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

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

Neuron 311 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: 5.0531. Min Range: -5.0531

Max Act: 5.0531. Min Act: -0.1700

Data Index: 108367 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.9906. Min Act: -0.1700

Data Index: 608055 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.8969. Min Act: -0.1700

Data Index: 161217 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.8656. Min Act: -0.1700

Data Index: 1012302 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.8656. Min Act: -0.1700

Data Index: 295563 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.8031. Min Act: -0.1700

Data Index: 405107 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.8344. Min Act: -0.1700

Data Index: 295696 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7719. Min Act: -0.1700

Data Index: 1126488 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7719. Min Act: -0.1700

Data Index: 450231 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7719. Min Act: -0.1700

Data Index: 104917 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7094. Min Act: -0.1700

Data Index: 175377 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7719. Min Act: -0.1700

Data Index: 139833 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7094. Min Act: -0.1700

Data Index: 60654 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7094. Min Act: -0.1700

Data Index: 561526 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7094. Min Act: -0.1700

Data Index: 1099711 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7094. Min Act: -0.1700

Data Index: 367565 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7094. Min Act: -0.1700

Data Index: 221204 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7094. Min Act: -0.1700

Data Index: 793545 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.7094. Min Act: -0.1700

Data Index: 660168 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 5.0531. Min Range: -5.0531

Max Act: 4.6781. Min Act: -0.1700

Data Index: 522773 (C4 (Web Text))

Max Activating Token Index: 175