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

Dataset: Open Web Text

Neuron 2496 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: 7.6143. Min Range: -7.6143

Max Act: 7.6143. Min Act: -0.1700

Data Index: 914573 (Open Web Text)

Max Activating Token Index: 1018

Text #1

Max Range: 7.6143. Min Range: -7.6143

Max Act: 7.1489. Min Act: -0.1700

Data Index: 5118881 (Open Web Text)

Max Activating Token Index: 726

Text #2

Max Range: 7.6143. Min Range: -7.6143

Max Act: 7.1343. Min Act: -0.1700

Data Index: 6858290 (Open Web Text)

Max Activating Token Index: 602

Text #3

Max Range: 7.6143. Min Range: -7.6143

Max Act: 7.0611. Min Act: -0.1700

Data Index: 5073317 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 7.6143. Min Range: -7.6143

Max Act: 7.0104. Min Act: -0.1700

Data Index: 5601921 (Open Web Text)

Max Activating Token Index: 194

Text #5

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.9625. Min Act: -0.1700

Data Index: 1589641 (Open Web Text)

Max Activating Token Index: 368

Text #6

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.9833. Min Act: -0.1700

Data Index: 4774767 (Open Web Text)

Max Activating Token Index: 147

Text #7

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.9662. Min Act: -0.1700

Data Index: 1147378 (Open Web Text)

Max Activating Token Index: 754

Text #8

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8906. Min Act: -0.1700

Data Index: 569298 (Open Web Text)

Max Activating Token Index: 286

Text #9

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8676. Min Act: -0.1700

Data Index: 2257369 (Open Web Text)

Max Activating Token Index: 973

Text #10

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.9016. Min Act: -0.1700

Data Index: 7792907 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8966. Min Act: -0.1700

Data Index: 7375339 (Open Web Text)

Max Activating Token Index: 964

Text #12

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8387. Min Act: -0.1700

Data Index: 5703855 (Open Web Text)

Max Activating Token Index: 888

Text #13

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8654. Min Act: -0.1700

Data Index: 2465660 (Open Web Text)

Max Activating Token Index: 314

Text #14

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.9467. Min Act: -0.1700

Data Index: 7294785 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8567. Min Act: -0.1700

Data Index: 8793805 (Open Web Text)

Max Activating Token Index: 572

Text #16

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8306. Min Act: -0.1700

Data Index: 2125436 (Open Web Text)

Max Activating Token Index: 469

Text #17

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8154. Min Act: -0.1700

Data Index: 2827796 (Open Web Text)

Max Activating Token Index: 509

Text #18

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8361. Min Act: -0.1700

Data Index: 6247160 (Open Web Text)

Max Activating Token Index: 804

Text #19

Max Range: 7.6143. Min Range: -7.6143

Max Act: 6.8444. Min Act: -0.1700

Data Index: 1535126 (Open Web Text)

Max Activating Token Index: 365