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

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

Neuron 1150 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: 3.1624. Min Range: -3.1624

Max Act: 3.1624. Min Act: -0.1700

Data Index: 1476994 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0609. Min Act: -0.1700

Data Index: 871779 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0595. Min Act: -0.1700

Data Index: 155527 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0362. Min Act: -0.1700

Data Index: 208905 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0372. Min Act: -0.1700

Data Index: 1203221 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0056. Min Act: -0.1700

Data Index: 1427666 (Python Code)

Max Activating Token Index: 486

Text #6

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0074. Min Act: -0.1700

Data Index: 1653730 (Python Code)

Max Activating Token Index: 994

Text #7

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0337. Min Act: -0.1700

Data Index: 1076679 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9845. Min Act: -0.1700

Data Index: 1370446 (Python Code)

Max Activating Token Index: 1019

Text #9

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9893. Min Act: -0.1700

Data Index: 976727 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.1624. Min Range: -3.1624

Max Act: 3.0089. Min Act: -0.1700

Data Index: 162780 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9762. Min Act: -0.1700

Data Index: 69639 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9861. Min Act: -0.1700

Data Index: 263221 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9688. Min Act: -0.1700

Data Index: 209379 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9556. Min Act: -0.1700

Data Index: 1633903 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9693. Min Act: -0.1700

Data Index: 359082 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9809. Min Act: -0.1700

Data Index: 393402 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9747. Min Act: -0.1700

Data Index: 1566734 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9670. Min Act: -0.1700

Data Index: 914405 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 3.1624. Min Range: -3.1624

Max Act: 2.9260. Min Act: -0.1700

Data Index: 141961 (C4 (Web Text))

Max Activating Token Index: 951