Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1835 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.8877. Min Act: -0.1700

Data Index: 683355 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7939. Min Act: -0.1700

Data Index: 179037 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7939. Min Act: -0.1700

Data Index: 657580 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.8095. Min Act: -0.1700

Data Index: 760660 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7000. Min Act: -0.1700

Data Index: 1053640 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7000. Min Act: -0.1700

Data Index: 1269202 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7157. Min Act: -0.1700

Data Index: 1327735 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7626. Min Act: -0.1700

Data Index: 647604 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.7157. Min Act: -0.1700

Data Index: 954575 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.5748. Min Act: -0.1700

Data Index: 330983 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.5905. Min Act: -0.1700

Data Index: 1229618 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.6061. Min Act: -0.1700

Data Index: 767127 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.6374. Min Act: -0.1700

Data Index: 189594 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.5591. Min Act: -0.1700

Data Index: 236105 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.6061. Min Act: -0.1700

Data Index: 503619 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.5122. Min Act: -0.1700

Data Index: 1130748 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.5435. Min Act: -0.1700

Data Index: 702393 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.4965. Min Act: -0.1700

Data Index: 264957 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.5435. Min Act: -0.1700

Data Index: 383197 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 3.8877. Min Range: -3.8877

Max Act: 3.5435. Min Act: -0.1700

Data Index: 1092504 (C4 (Web Text))

Max Activating Token Index: 60