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

Dataset: Open Web Text

Neuron 605 in Layer 2

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: 1.6602. Min Range: -1.6602

Max Act: 1.6602. Min Act: -0.1700

Data Index: 2846877 (Open Web Text)

Max Activating Token Index: 902

Text #1

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.3722. Min Act: -0.1700

Data Index: 3165296 (Open Web Text)

Max Activating Token Index: 226

Text #2

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.3520. Min Act: -0.1692

Data Index: 2403608 (Open Web Text)

Max Activating Token Index: 341

Text #3

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.3142. Min Act: -0.1700

Data Index: 7312303 (Open Web Text)

Max Activating Token Index: 457

Text #4

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2777. Min Act: -0.1700

Data Index: 2954933 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2551. Min Act: -0.1699

Data Index: 8500779 (Open Web Text)

Max Activating Token Index: 421

Text #6

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2581. Min Act: -0.1700

Data Index: 4198615 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2579. Min Act: -0.1697

Data Index: 4350122 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2390. Min Act: -0.1695

Data Index: 7664981 (Open Web Text)

Max Activating Token Index: 939

Text #9

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2345. Min Act: -0.1698

Data Index: 727467 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2345. Min Act: -0.1696

Data Index: 5857872 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2345. Min Act: -0.1685

Data Index: 7839743 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2269. Min Act: -0.1700

Data Index: 1231781 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2238. Min Act: -0.1696

Data Index: 2150524 (Open Web Text)

Max Activating Token Index: 76

Text #14

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.1827. Min Act: -0.1700

Data Index: 5258824 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.2053. Min Act: -0.1699

Data Index: 6358623 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.1942. Min Act: -0.1700

Data Index: 1157865 (Open Web Text)

Max Activating Token Index: 137

Text #17

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.1947. Min Act: -0.1700

Data Index: 4094304 (Open Web Text)

Max Activating Token Index: 497

Text #18

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.1872. Min Act: -0.1671

Data Index: 1422955 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.6602. Min Range: -1.6602

Max Act: 1.1701. Min Act: -0.1700

Data Index: 6548123 (Open Web Text)

Max Activating Token Index: 116