Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2755 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.3687. Min Act: -0.1700

Data Index: 4414673 (Open Web Text)

Max Activating Token Index: 434

Text #1

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.3550. Min Act: -0.1700

Data Index: 6641577 (Open Web Text)

Max Activating Token Index: 493

Text #2

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.3123. Min Act: -0.1700

Data Index: 1466528 (Open Web Text)

Max Activating Token Index: 671

Text #3

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.3316. Min Act: -0.1700

Data Index: 2649400 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2888. Min Act: -0.1700

Data Index: 5118458 (Open Web Text)

Max Activating Token Index: 737

Text #5

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2829. Min Act: -0.1700

Data Index: 6213127 (Open Web Text)

Max Activating Token Index: 371

Text #6

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2912. Min Act: -0.1699

Data Index: 182678 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2941. Min Act: -0.1700

Data Index: 5883733 (Open Web Text)

Max Activating Token Index: 606

Text #8

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2708. Min Act: -0.1700

Data Index: 5722269 (Open Web Text)

Max Activating Token Index: 455

Text #9

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2778. Min Act: -0.1700

Data Index: 8478378 (Open Web Text)

Max Activating Token Index: 620

Text #10

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2643. Min Act: -0.1700

Data Index: 5687149 (Open Web Text)

Max Activating Token Index: 395

Text #11

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.3079. Min Act: -0.1700

Data Index: 1453034 (Open Web Text)

Max Activating Token Index: 664

Text #12

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2656. Min Act: -0.1700

Data Index: 8279214 (Open Web Text)

Max Activating Token Index: 818

Text #13

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2660. Min Act: -0.1700

Data Index: 7428746 (Open Web Text)

Max Activating Token Index: 312

Text #14

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2734. Min Act: -0.1700

Data Index: 4024132 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2653. Min Act: -0.1700

Data Index: 7233874 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2759. Min Act: -0.1700

Data Index: 6975916 (Open Web Text)

Max Activating Token Index: 645

Text #17

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2784. Min Act: -0.1700

Data Index: 3543117 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2603. Min Act: -0.1700

Data Index: 5895693 (Open Web Text)

Max Activating Token Index: 656

Text #19

Max Range: 4.3687. Min Range: -4.3687

Max Act: 4.2627. Min Act: -0.1700

Data Index: 6250492 (Open Web Text)

Max Activating Token Index: 735