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

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

Neuron 392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3126. Min Range: -5.3126

Max Act: 5.2814. Min Act: -0.1700

Data Index: 632128 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 5.3126. Min Range: -5.3126

Max Act: 5.3126. Min Act: -0.1700

Data Index: 560480 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 5.3126. Min Range: -5.3126

Max Act: 5.2189. Min Act: -0.1700

Data Index: 1344665 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 5.3126. Min Range: -5.3126

Max Act: 5.1251. Min Act: -0.1700

Data Index: 644701 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 5.3126. Min Range: -5.3126

Max Act: 5.0626. Min Act: -0.1700

Data Index: 1239761 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 5.3126. Min Range: -5.3126

Max Act: 5.0314. Min Act: -0.1700

Data Index: 928109 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 5.3126. Min Range: -5.3126

Max Act: 5.0626. Min Act: -0.1700

Data Index: 19559 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.9376. Min Act: -0.1700

Data Index: 293681 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.9064. Min Act: -0.1700

Data Index: 1019016 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.8751. Min Act: -0.1700

Data Index: 1169377 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.9064. Min Act: -0.1700

Data Index: 84106 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.8126. Min Act: -0.1700

Data Index: 989514 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.7814. Min Act: -0.1700

Data Index: 59370 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.7501. Min Act: -0.1699

Data Index: 955589 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.7189. Min Act: -0.1700

Data Index: 230801 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.7501. Min Act: -0.1700

Data Index: 1093200 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.7501. Min Act: -0.1700

Data Index: 703563 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.7501. Min Act: -0.1700

Data Index: 759961 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.7032. Min Act: -0.1700

Data Index: 1228942 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 5.3126. Min Range: -5.3126

Max Act: 4.7501. Min Act: -0.1700

Data Index: 1201600 (C4 (Web Text))

Max Activating Token Index: 113