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

Dataset: Open Web Text

Neuron 772 in Layer 3

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: 2.8697. Min Range: -2.8697

Max Act: 2.8682. Min Act: -0.1700

Data Index: 2838389 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.8697. Min Act: -0.1700

Data Index: 1124559 (Open Web Text)

Max Activating Token Index: 476

Text #2

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.8245. Min Act: -0.1700

Data Index: 6251121 (Open Web Text)

Max Activating Token Index: 149

Text #3

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.8382. Min Act: -0.1700

Data Index: 5994253 (Open Web Text)

Max Activating Token Index: 285

Text #4

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.8427. Min Act: -0.1700

Data Index: 784726 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.8386. Min Act: -0.1700

Data Index: 703310 (Open Web Text)

Max Activating Token Index: 590

Text #6

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.8005. Min Act: -0.1700

Data Index: 5587796 (Open Web Text)

Max Activating Token Index: 558

Text #7

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.8204. Min Act: -0.1700

Data Index: 6083002 (Open Web Text)

Max Activating Token Index: 230

Text #8

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7972. Min Act: -0.1700

Data Index: 1894249 (Open Web Text)

Max Activating Token Index: 428

Text #9

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7995. Min Act: -0.1700

Data Index: 915919 (Open Web Text)

Max Activating Token Index: 699

Text #10

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7990. Min Act: -0.1700

Data Index: 4839758 (Open Web Text)

Max Activating Token Index: 184

Text #11

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7757. Min Act: -0.1700

Data Index: 6705245 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.8235. Min Act: -0.1700

Data Index: 3308747 (Open Web Text)

Max Activating Token Index: 867

Text #13

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7536. Min Act: -0.1700

Data Index: 2153373 (Open Web Text)

Max Activating Token Index: 786

Text #14

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7655. Min Act: -0.1700

Data Index: 8206748 (Open Web Text)

Max Activating Token Index: 555

Text #15

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7474. Min Act: -0.1700

Data Index: 2365390 (Open Web Text)

Max Activating Token Index: 187

Text #16

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7852. Min Act: -0.1700

Data Index: 6852595 (Open Web Text)

Max Activating Token Index: 833

Text #17

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7751. Min Act: -0.1700

Data Index: 1589618 (Open Web Text)

Max Activating Token Index: 858

Text #18

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7627. Min Act: -0.1700

Data Index: 2717850 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 2.8697. Min Range: -2.8697

Max Act: 2.7538. Min Act: -0.1700

Data Index: 5182020 (Open Web Text)

Max Activating Token Index: 681