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

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

Neuron 1491 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1631. Min Range: -4.1631

Max Act: 4.1631. Min Act: -0.1700

Data Index: 1267202 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.9755. Min Act: -0.1700

Data Index: 1219934 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8817. Min Act: -0.1700

Data Index: 806839 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.9130. Min Act: -0.1700

Data Index: 949589 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.9443. Min Act: -0.1700

Data Index: 222204 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.9130. Min Act: -0.1700

Data Index: 109454 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8817. Min Act: -0.1700

Data Index: 961240 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 4.1631. Min Range: -4.1631

Max Act: 4.0068. Min Act: -0.1700

Data Index: 65240 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.9443. Min Act: -0.1700

Data Index: 129676 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8817. Min Act: -0.1700

Data Index: 118098 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8817. Min Act: -0.1700

Data Index: 16384 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.9130. Min Act: -0.1700

Data Index: 951091 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8505. Min Act: -0.1700

Data Index: 1081594 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8817. Min Act: -0.1700

Data Index: 823424 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8505. Min Act: -0.1700

Data Index: 1030847 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.7879. Min Act: -0.1700

Data Index: 1065942 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.7879. Min Act: -0.1700

Data Index: 500420 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8505. Min Act: -0.1700

Data Index: 491613 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.7566. Min Act: -0.1700

Data Index: 957785 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8505. Min Act: -0.1700

Data Index: 638593 (C4 (Web Text))

Max Activating Token Index: 712