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

Dataset: Open Web Text

Neuron 2295 in Layer 5

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: 4.0719. Min Range: -4.0719

Max Act: 4.0467. Min Act: -0.1700

Data Index: 5288648 (Open Web Text)

Max Activating Token Index: 583

Text #1

Max Range: 4.0719. Min Range: -4.0719

Max Act: 4.0719. Min Act: -0.1700

Data Index: 3682864 (Open Web Text)

Max Activating Token Index: 185

Text #2

Max Range: 4.0719. Min Range: -4.0719

Max Act: 4.0015. Min Act: -0.1700

Data Index: 7443814 (Open Web Text)

Max Activating Token Index: 808

Text #3

Max Range: 4.0719. Min Range: -4.0719

Max Act: 4.0097. Min Act: -0.1700

Data Index: 7421961 (Open Web Text)

Max Activating Token Index: 507

Text #4

Max Range: 4.0719. Min Range: -4.0719

Max Act: 4.0036. Min Act: -0.1700

Data Index: 1415968 (Open Web Text)

Max Activating Token Index: 157

Text #5

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9926. Min Act: -0.1700

Data Index: 1177613 (Open Web Text)

Max Activating Token Index: 914

Text #6

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9787. Min Act: -0.1700

Data Index: 4224724 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9511. Min Act: -0.1700

Data Index: 4279223 (Open Web Text)

Max Activating Token Index: 693

Text #8

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9732. Min Act: -0.1700

Data Index: 8151943 (Open Web Text)

Max Activating Token Index: 714

Text #9

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9485. Min Act: -0.1700

Data Index: 5101266 (Open Web Text)

Max Activating Token Index: 384

Text #10

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9255. Min Act: -0.1700

Data Index: 1962343 (Open Web Text)

Max Activating Token Index: 301

Text #11

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9310. Min Act: -0.1700

Data Index: 6787334 (Open Web Text)

Max Activating Token Index: 987

Text #12

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9022. Min Act: -0.1700

Data Index: 8029578 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.8934. Min Act: -0.1700

Data Index: 2666357 (Open Web Text)

Max Activating Token Index: 820

Text #14

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.9014. Min Act: -0.1700

Data Index: 6126254 (Open Web Text)

Max Activating Token Index: 246

Text #15

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.8568. Min Act: -0.1700

Data Index: 8263579 (Open Web Text)

Max Activating Token Index: 723

Text #16

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.8878. Min Act: -0.1700

Data Index: 5334989 (Open Web Text)

Max Activating Token Index: 175

Text #17

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.8831. Min Act: -0.1700

Data Index: 1054186 (Open Web Text)

Max Activating Token Index: 234

Text #18

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.8394. Min Act: -0.1700

Data Index: 8742878 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 4.0719. Min Range: -4.0719

Max Act: 3.8592. Min Act: -0.1700

Data Index: 3034247 (Open Web Text)

Max Activating Token Index: 475