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

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

Neuron 1306 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: 5.5243. Min Range: -5.5243

Max Act: 5.5243. Min Act: -0.1700

Data Index: 1049031 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.3993. Min Act: -0.1700

Data Index: 390492 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.3056. Min Act: -0.1700

Data Index: 956650 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.2118. Min Act: -0.1700

Data Index: 476512 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.1493. Min Act: -0.1700

Data Index: 716678 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0243. Min Act: -0.1700

Data Index: 1274660 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 5.5243. Min Range: -5.5243

Max Act: 5.0868. Min Act: -0.1700

Data Index: 1289149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.9931. Min Act: -0.1700

Data Index: 941053 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.8993. Min Act: -0.1700

Data Index: 294486 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.9306. Min Act: -0.1700

Data Index: 910659 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.9618. Min Act: -0.1700

Data Index: 379516 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.9306. Min Act: -0.1700

Data Index: 947967 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.8993. Min Act: -0.1700

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.9618. Min Act: -0.1700

Data Index: 135798 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.8993. Min Act: -0.1700

Data Index: 1205064 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.9618. Min Act: -0.1700

Data Index: 507334 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.8681. Min Act: -0.1700

Data Index: 427009 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.8368. Min Act: -0.1700

Data Index: 1066283 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.7743. Min Act: -0.1700

Data Index: 658848 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 5.5243. Min Range: -5.5243

Max Act: 4.7431. Min Act: -0.1700

Data Index: 538519 (C4 (Web Text))

Max Activating Token Index: 396