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

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

Neuron 1234 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: 5.5417. Min Range: -5.5417

Max Act: 5.5417. Min Act: -0.1700

Data Index: 1109877 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.5417. Min Act: -0.1700

Data Index: 814345 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.5104. Min Act: -0.1700

Data Index: 262866 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4792. Min Act: -0.1700

Data Index: 345207 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 1357384 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4479. Min Act: -0.1700

Data Index: 536943 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3854. Min Act: -0.1700

Data Index: 920038 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 1181492 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 349997 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3854. Min Act: -0.1700

Data Index: 979554 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4479. Min Act: -0.1700

Data Index: 1012336 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3854. Min Act: -0.1700

Data Index: 944991 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 1265605 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 352318 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 27318 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 749296 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 880516 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 350900 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3229. Min Act: -0.1700

Data Index: 285101 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 787183 (C4 (Web Text))

Max Activating Token Index: 17