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

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

Neuron 1798 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: 8.0366. Min Range: -8.0366

Max Act: 8.0366. Min Act: -0.1700

Data Index: 322118 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.8804. Min Act: -0.1700

Data Index: 1237879 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.8491. Min Act: -0.1700

Data Index: 671012 (C4 (Web Text))

Max Activating Token Index: 967

Text #3

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.8491. Min Act: -0.1700

Data Index: 262894 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.8179. Min Act: -0.1700

Data Index: 958459 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.6929. Min Act: -0.1700

Data Index: 854094 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.6929. Min Act: -0.1700

Data Index: 228711 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5366. Min Act: -0.1700

Data Index: 665093 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5679. Min Act: -0.1700

Data Index: 1040855 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.6304. Min Act: -0.1700

Data Index: 152877 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5679. Min Act: -0.1700

Data Index: 966712 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5366. Min Act: -0.1700

Data Index: 1038311 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5679. Min Act: -0.1700

Data Index: 173132 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5054. Min Act: -0.1700

Data Index: 446209 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5054. Min Act: -0.1700

Data Index: 277049 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5366. Min Act: -0.1700

Data Index: 88477 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.5054. Min Act: -0.1700

Data Index: 544283 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.4741. Min Act: -0.1700

Data Index: 932185 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.4741. Min Act: -0.1700

Data Index: 44935 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 8.0366. Min Range: -8.0366

Max Act: 7.4429. Min Act: -0.1700

Data Index: 32195 (C4 (Web Text))

Max Activating Token Index: 438