Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1992 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.5378. Min Act: -0.1700

Data Index: 76448 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.4753. Min Act: -0.1700

Data Index: 1250742 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.3190. Min Act: -0.1700

Data Index: 214256 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.3815. Min Act: -0.1700

Data Index: 1292885 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.3815. Min Act: -0.1700

Data Index: 142109 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.3815. Min Act: -0.1700

Data Index: 152897 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.3503. Min Act: -0.1700

Data Index: 249883 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2878. Min Act: -0.1700

Data Index: 1090899 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2878. Min Act: -0.1700

Data Index: 510991 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2878. Min Act: -0.1700

Data Index: 1313982 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2878. Min Act: -0.1700

Data Index: 1334718 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2878. Min Act: -0.1700

Data Index: 450336 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2878. Min Act: -0.1700

Data Index: 894851 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2878. Min Act: -0.1700

Data Index: 749923 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2253. Min Act: -0.1700

Data Index: 645590 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2878. Min Act: -0.1700

Data Index: 1080066 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2565. Min Act: -0.1700

Data Index: 941221 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2253. Min Act: -0.1700

Data Index: 1214231 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.1940. Min Act: -0.1700

Data Index: 1116328 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 5.5378. Min Range: -5.5378

Max Act: 5.2253. Min Act: -0.1700

Data Index: 1119609 (C4 (Web Text))

Max Activating Token Index: 174