Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 209 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1119. Min Range: -5.1119

Max Act: 5.1119. Min Act: -0.1700

Data Index: 1331586 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 5.1119. Min Range: -5.1119

Max Act: 5.1119. Min Act: -0.1700

Data Index: 1250062 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 5.1119. Min Range: -5.1119

Max Act: 5.0494. Min Act: -0.1700

Data Index: 272174 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 5.1119. Min Range: -5.1119

Max Act: 5.0181. Min Act: -0.1698

Data Index: 460986 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.9244. Min Act: -0.1700

Data Index: 179218 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.9556. Min Act: -0.1700

Data Index: 105147 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8931. Min Act: -0.1700

Data Index: 1204684 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8931. Min Act: -0.1700

Data Index: 347968 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8619. Min Act: -0.1700

Data Index: 1035860 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8306. Min Act: -0.1700

Data Index: 1280491 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8931. Min Act: -0.1700

Data Index: 176382 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8306. Min Act: -0.1700

Data Index: 265799 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8619. Min Act: -0.1700

Data Index: 545198 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.7681. Min Act: -0.1700

Data Index: 338125 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8306. Min Act: -0.1700

Data Index: 95951 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.7994. Min Act: -0.1700

Data Index: 177738 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8619. Min Act: -0.1700

Data Index: 707506 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8306. Min Act: -0.1700

Data Index: 114999 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.8306. Min Act: -0.1700

Data Index: 213938 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 5.1119. Min Range: -5.1119

Max Act: 4.7681. Min Act: -0.1700

Data Index: 334353 (C4 (Web Text))

Max Activating Token Index: 16