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

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

Neuron 486 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: 5.5956. Min Range: -5.5956

Max Act: 5.5956. Min Act: -0.1700

Data Index: 185074 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.5019. Min Act: -0.1700

Data Index: 1076647 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.4706. Min Act: -0.1700

Data Index: 130952 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.5019. Min Act: -0.1700

Data Index: 328877 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.4706. Min Act: -0.1700

Data Index: 342014 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.4394. Min Act: -0.1700

Data Index: 368391 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.4081. Min Act: -0.1700

Data Index: 852742 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.4081. Min Act: -0.1700

Data Index: 274722 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.4081. Min Act: -0.1700

Data Index: 198060 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.4081. Min Act: -0.1700

Data Index: 760236 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.3456. Min Act: -0.1700

Data Index: 953140 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.3769. Min Act: -0.1700

Data Index: 1299301 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.3769. Min Act: -0.1700

Data Index: 544352 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.3144. Min Act: -0.1700

Data Index: 242941 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.2831. Min Act: -0.1700

Data Index: 266741 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.3456. Min Act: -0.1700

Data Index: 393860 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.2831. Min Act: -0.1700

Data Index: 13854 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.3144. Min Act: -0.1700

Data Index: 65528 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.3769. Min Act: -0.1700

Data Index: 175330 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 5.5956. Min Range: -5.5956

Max Act: 5.3769. Min Act: -0.1700

Data Index: 1222915 (C4 (Web Text))

Max Activating Token Index: 531