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

Dataset: Open Web Text

Neuron 1205 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: 3.2632. Min Range: -3.2632

Max Act: 3.2632. Min Act: -0.1700

Data Index: 7521119 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2623. Min Act: -0.1700

Data Index: 6031332 (Open Web Text)

Max Activating Token Index: 903

Text #2

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2524. Min Act: -0.1700

Data Index: 7135558 (Open Web Text)

Max Activating Token Index: 662

Text #3

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2291. Min Act: -0.1700

Data Index: 3487081 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2570. Min Act: -0.1700

Data Index: 8426416 (Open Web Text)

Max Activating Token Index: 859

Text #5

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2319. Min Act: -0.1700

Data Index: 3628112 (Open Web Text)

Max Activating Token Index: 715

Text #6

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2149. Min Act: -0.1700

Data Index: 7030920 (Open Web Text)

Max Activating Token Index: 930

Text #7

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2202. Min Act: -0.1700

Data Index: 7727084 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2210. Min Act: -0.1700

Data Index: 1401554 (Open Web Text)

Max Activating Token Index: 543

Text #9

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2051. Min Act: -0.1700

Data Index: 8132363 (Open Web Text)

Max Activating Token Index: 512

Text #10

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2071. Min Act: -0.1700

Data Index: 8138407 (Open Web Text)

Max Activating Token Index: 954

Text #11

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1625. Min Act: -0.1700

Data Index: 6122684 (Open Web Text)

Max Activating Token Index: 841

Text #12

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1886. Min Act: -0.1700

Data Index: 1330004 (Open Web Text)

Max Activating Token Index: 325

Text #13

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1994. Min Act: -0.1700

Data Index: 5862786 (Open Web Text)

Max Activating Token Index: 908

Text #14

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1990. Min Act: -0.1700

Data Index: 211809 (Open Web Text)

Max Activating Token Index: 329

Text #15

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.2041. Min Act: -0.1700

Data Index: 2989465 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1778. Min Act: -0.1700

Data Index: 2537394 (Open Web Text)

Max Activating Token Index: 344

Text #17

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1760. Min Act: -0.1700

Data Index: 4017558 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1842. Min Act: -0.1700

Data Index: 6631441 (Open Web Text)

Max Activating Token Index: 530

Text #19

Max Range: 3.2632. Min Range: -3.2632

Max Act: 3.1283. Min Act: -0.1700

Data Index: 5933661 (Open Web Text)

Max Activating Token Index: 1006