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

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

Neuron 1106 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: 3.4995. Min Range: -3.4995

Max Act: 3.4995. Min Act: -0.1700

Data Index: 1435297 (Python Code)

Max Activating Token Index: 644

Text #1

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.4627. Min Act: -0.1700

Data Index: 1599458 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1440341 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3646. Min Act: -0.1700

Data Index: 801030 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3895. Min Act: -0.1700

Data Index: 904929 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3734. Min Act: -0.1700

Data Index: 1370055 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3757. Min Act: -0.1700

Data Index: 778915 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3730. Min Act: -0.1700

Data Index: 375706 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3933. Min Act: -0.1700

Data Index: 378491 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.4100. Min Act: -0.1700

Data Index: 1006943 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3472. Min Act: -0.1700

Data Index: 1172226 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3642. Min Act: -0.1700

Data Index: 380228 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3433. Min Act: -0.1700

Data Index: 984414 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3374. Min Act: -0.1700

Data Index: 451010 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3315. Min Act: -0.1700

Data Index: 3468 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3418. Min Act: -0.1700

Data Index: 1211879 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3217. Min Act: -0.1700

Data Index: 503164 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3397. Min Act: -0.1700

Data Index: 1176366 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3459. Min Act: -0.1700

Data Index: 1084746 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 3.4995. Min Range: -3.4995

Max Act: 3.3173. Min Act: -0.1700

Data Index: 1464666 (Python Code)

Max Activating Token Index: 862