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

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

Neuron 918 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: 3.3808. Min Range: -3.3808

Max Act: 3.3808. Min Act: -0.1700

Data Index: 1332194 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.3495. Min Act: -0.1700

Data Index: 689469 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.2552. Min Act: -0.1700

Data Index: 1122521 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.2081. Min Act: -0.1700

Data Index: 726070 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.1136. Min Act: -0.1700

Data Index: 365642 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0663. Min Act: -0.1700

Data Index: 967903 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0663. Min Act: -0.1700

Data Index: 11215 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0347. Min Act: -0.1700

Data Index: 1631838 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 3.3808. Min Range: -3.3808

Max Act: 2.9873. Min Act: -0.1700

Data Index: 216779 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0189. Min Act: -0.1700

Data Index: 476631 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0189. Min Act: -0.1700

Data Index: 476510 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0347. Min Act: -0.1700

Data Index: 1201642 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0347. Min Act: -0.1700

Data Index: 1228407 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0031. Min Act: -0.1700

Data Index: 917839 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0189. Min Act: -0.1700

Data Index: 467669 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0347. Min Act: -0.1700

Data Index: 97263 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0347. Min Act: -0.1700

Data Index: 1254500 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 3.3808. Min Range: -3.3808

Max Act: 2.9873. Min Act: -0.1700

Data Index: 541764 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 3.3808. Min Range: -3.3808

Max Act: 2.9398. Min Act: -0.1700

Data Index: 1006669 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 3.3808. Min Range: -3.3808

Max Act: 3.0031. Min Act: -0.1700

Data Index: 413943 (C4 (Web Text))

Max Activating Token Index: 533