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

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

Neuron 1948 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: 4.0561. Min Range: -4.0561

Max Act: 4.0561. Min Act: -0.1700

Data Index: 1316055 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 4.0561. Min Range: -4.0561

Max Act: 4.0345. Min Act: -0.1700

Data Index: 701986 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 4.0561. Min Range: -4.0561

Max Act: 4.0559. Min Act: -0.1700

Data Index: 25850 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 4.0561. Min Range: -4.0561

Max Act: 4.0006. Min Act: -0.1700

Data Index: 1068436 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 4.0561. Min Range: -4.0561

Max Act: 4.0254. Min Act: -0.1700

Data Index: 1320763 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9937. Min Act: -0.1700

Data Index: 1084069 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9622. Min Act: -0.1700

Data Index: 369619 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9726. Min Act: -0.1700

Data Index: 415506 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9565. Min Act: -0.1700

Data Index: 502740 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9748. Min Act: -0.1700

Data Index: 424298 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9939. Min Act: -0.1700

Data Index: 103809 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9784. Min Act: -0.1700

Data Index: 27283 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9918. Min Act: -0.1700

Data Index: 880106 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9709. Min Act: -0.1700

Data Index: 316374 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9520. Min Act: -0.1700

Data Index: 1030291 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9585. Min Act: -0.1700

Data Index: 514420 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9128. Min Act: -0.1700

Data Index: 956998 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9454. Min Act: -0.1700

Data Index: 831782 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9489. Min Act: -0.1700

Data Index: 313572 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 4.0561. Min Range: -4.0561

Max Act: 3.9492. Min Act: -0.1700

Data Index: 1055034 (C4 (Web Text))

Max Activating Token Index: 183