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

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

Neuron 230 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3767. Min Range: -6.3767

Max Act: 6.3767. Min Act: -0.1700

Data Index: 1464595 (Python Code)

Max Activating Token Index: 528

Text #1

Max Range: 6.3767. Min Range: -6.3767

Max Act: 6.2205. Min Act: -0.1700

Data Index: 1576825 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 6.3767. Min Range: -6.3767

Max Act: 6.1892. Min Act: -0.1700

Data Index: 1365833 (Python Code)

Max Activating Token Index: 819

Text #3

Max Range: 6.3767. Min Range: -6.3767

Max Act: 6.0642. Min Act: -0.1700

Data Index: 1592306 (Python Code)

Max Activating Token Index: 866

Text #4

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.9392. Min Act: -0.1700

Data Index: 1513652 (Python Code)

Max Activating Token Index: 619

Text #5

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.9080. Min Act: -0.1700

Data Index: 1383630 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.8767. Min Act: -0.1700

Data Index: 1525340 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.8455. Min Act: -0.1700

Data Index: 1495122 (Python Code)

Max Activating Token Index: 178

Text #8

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.8142. Min Act: -0.1700

Data Index: 1380291 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.8455. Min Act: -0.1700

Data Index: 1556569 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.7830. Min Act: -0.1700

Data Index: 1498318 (Python Code)

Max Activating Token Index: 905

Text #11

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.7205. Min Act: -0.1700

Data Index: 1361329 (Python Code)

Max Activating Token Index: 899

Text #12

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.7517. Min Act: -0.1700

Data Index: 1538071 (Python Code)

Max Activating Token Index: 707

Text #13

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.6267. Min Act: -0.1700

Data Index: 1411251 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.6580. Min Act: -0.1700

Data Index: 1147678 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.6267. Min Act: -0.1700

Data Index: 628223 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.5955. Min Act: -0.1700

Data Index: 28127 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.6267. Min Act: -0.1700

Data Index: 669343 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.6267. Min Act: -0.1700

Data Index: 1476655 (Python Code)

Max Activating Token Index: 830

Text #19

Max Range: 6.3767. Min Range: -6.3767

Max Act: 5.6267. Min Act: -0.1700

Data Index: 1473894 (Python Code)

Max Activating Token Index: 890