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

Dataset: Open Web Text

Neuron 1806 in Layer 0

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: 4.5439. Min Range: -4.5439

Max Act: 4.5439. Min Act: -0.1700

Data Index: 49624 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.3651. Min Act: -0.1700

Data Index: 7932637 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.3507. Min Act: -0.1700

Data Index: 3338302 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.3426. Min Act: -0.1700

Data Index: 3182637 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.3222. Min Act: -0.1700

Data Index: 3871142 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2675. Min Act: -0.1700

Data Index: 5510528 (Open Web Text)

Max Activating Token Index: 937

Text #6

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2768. Min Act: -0.1700

Data Index: 8567679 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2770. Min Act: -0.1700

Data Index: 3048837 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2547. Min Act: -0.1700

Data Index: 8136289 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2416. Min Act: -0.1700

Data Index: 5117273 (Open Web Text)

Max Activating Token Index: 746

Text #10

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2430. Min Act: -0.1700

Data Index: 1051612 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2469. Min Act: -0.1700

Data Index: 3433980 (Open Web Text)

Max Activating Token Index: 20

Text #12

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2350. Min Act: -0.1700

Data Index: 8173135 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2491. Min Act: -0.1700

Data Index: 5835922 (Open Web Text)

Max Activating Token Index: 591

Text #14

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2606. Min Act: -0.1700

Data Index: 2254370 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2583. Min Act: -0.1700

Data Index: 3003783 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2366. Min Act: -0.1700

Data Index: 7530828 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2725. Min Act: -0.1700

Data Index: 8705925 (Open Web Text)

Max Activating Token Index: 57

Text #18

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2604. Min Act: -0.1700

Data Index: 975063 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 4.5439. Min Range: -4.5439

Max Act: 4.2705. Min Act: -0.1700

Data Index: 6567027 (Open Web Text)

Max Activating Token Index: 6