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

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

Neuron 68 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.0024. Min Range: -4.0024

Max Act: 4.0024. Min Act: -0.1700

Data Index: 1004571 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9399. Min Act: -0.1700

Data Index: 637597 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9711. Min Act: -0.1700

Data Index: 629534 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9399. Min Act: -0.1700

Data Index: 1346893 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9086. Min Act: -0.1700

Data Index: 714929 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8773. Min Act: -0.1700

Data Index: 419352 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9086. Min Act: -0.1700

Data Index: 526000 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8773. Min Act: -0.1700

Data Index: 299182 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8773. Min Act: -0.1700

Data Index: 789152 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9086. Min Act: -0.1700

Data Index: 279579 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9399. Min Act: -0.1700

Data Index: 72682 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9711. Min Act: -0.1700

Data Index: 969873 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8460. Min Act: -0.1700

Data Index: 1008720 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8773. Min Act: -0.1700

Data Index: 82573 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.9086. Min Act: -0.1700

Data Index: 1128220 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8460. Min Act: -0.1700

Data Index: 1306889 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8773. Min Act: -0.1700

Data Index: 828653 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8773. Min Act: -0.1700

Data Index: 109014 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8773. Min Act: -0.1700

Data Index: 1008316 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 4.0024. Min Range: -4.0024

Max Act: 3.8460. Min Act: -0.1700

Data Index: 274098 (C4 (Web Text))

Max Activating Token Index: 766