Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1595 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.5509. Min Act: -0.1700

Data Index: 153452 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4973. Min Act: -0.1700

Data Index: 450787 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4697. Min Act: -0.1700

Data Index: 502913 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4625. Min Act: -0.1700

Data Index: 376317 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4620. Min Act: -0.1700

Data Index: 38812 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4600. Min Act: -0.1700

Data Index: 298136 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4370. Min Act: -0.1700

Data Index: 684044 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4234. Min Act: -0.1700

Data Index: 438845 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4529. Min Act: -0.1700

Data Index: 174608 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4057. Min Act: -0.1700

Data Index: 523768 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.3957. Min Act: -0.1700

Data Index: 221238 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4297. Min Act: -0.1700

Data Index: 109996 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4225. Min Act: -0.1700

Data Index: 437730 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.3913. Min Act: -0.1700

Data Index: 1061852 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4332. Min Act: -0.1700

Data Index: 663703 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.3872. Min Act: -0.1700

Data Index: 318203 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.3764. Min Act: -0.1700

Data Index: 1359245 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.4032. Min Act: -0.1700

Data Index: 1283855 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.3832. Min Act: -0.1700

Data Index: 999938 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 4.5509. Min Range: -4.5509

Max Act: 4.3705. Min Act: -0.1700

Data Index: 985979 (C4 (Web Text))

Max Activating Token Index: 944