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

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

Neuron 1049 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.6335. Min Act: -0.1700

Data Index: 285800 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.4142. Min Act: -0.1700

Data Index: 325593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.4298. Min Act: -0.1700

Data Index: 1211544 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.4455. Min Act: -0.1700

Data Index: 915201 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.4298. Min Act: -0.1700

Data Index: 284897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3828. Min Act: -0.1700

Data Index: 1338146 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3357. Min Act: -0.1700

Data Index: 639079 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3200. Min Act: -0.1700

Data Index: 1064481 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3514. Min Act: -0.1700

Data Index: 291851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3357. Min Act: -0.1700

Data Index: 562036 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3043. Min Act: -0.1700

Data Index: 754885 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.2886. Min Act: -0.1700

Data Index: 65828 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.2729. Min Act: -0.1700

Data Index: 748223 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3200. Min Act: -0.1700

Data Index: 901512 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.2572. Min Act: -0.1700

Data Index: 214060 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3043. Min Act: -0.1700

Data Index: 849222 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.2415. Min Act: -0.1700

Data Index: 73629 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.3043. Min Act: -0.1700

Data Index: 1045092 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.2886. Min Act: -0.1700

Data Index: 144564 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 3.6335. Min Range: -3.6335

Max Act: 3.2572. Min Act: -0.1700

Data Index: 561907 (C4 (Web Text))

Max Activating Token Index: 601