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

Dataset: Open Web Text

Neuron 1090 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: 5.4551. Min Range: -5.4551

Max Act: 5.4135. Min Act: -0.1700

Data Index: 7523260 (Open Web Text)

Max Activating Token Index: 326

Text #1

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.4551. Min Act: -0.1700

Data Index: 4830199 (Open Web Text)

Max Activating Token Index: 637

Text #2

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.3300. Min Act: -0.1700

Data Index: 5421351 (Open Web Text)

Max Activating Token Index: 569

Text #3

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.2647. Min Act: -0.1700

Data Index: 5727725 (Open Web Text)

Max Activating Token Index: 116

Text #4

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.2357. Min Act: -0.1700

Data Index: 4720339 (Open Web Text)

Max Activating Token Index: 493

Text #5

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.2028. Min Act: -0.1700

Data Index: 4188548 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.1470. Min Act: -0.1700

Data Index: 209624 (Open Web Text)

Max Activating Token Index: 242

Text #7

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.1181. Min Act: -0.1700

Data Index: 4414575 (Open Web Text)

Max Activating Token Index: 798

Text #8

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.0964. Min Act: -0.1700

Data Index: 8617380 (Open Web Text)

Max Activating Token Index: 594

Text #9

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.0833. Min Act: -0.1700

Data Index: 2962747 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.0614. Min Act: -0.1700

Data Index: 3176615 (Open Web Text)

Max Activating Token Index: 548

Text #11

Max Range: 5.4551. Min Range: -5.4551

Max Act: 5.0277. Min Act: -0.1700

Data Index: 3626814 (Open Web Text)

Max Activating Token Index: 157

Text #12

Max Range: 5.4551. Min Range: -5.4551

Max Act: 4.9836. Min Act: -0.1700

Data Index: 3233994 (Open Web Text)

Max Activating Token Index: 915

Text #13

Max Range: 5.4551. Min Range: -5.4551

Max Act: 4.9725. Min Act: -0.1700

Data Index: 5305062 (Open Web Text)

Max Activating Token Index: 272

Text #14

Max Range: 5.4551. Min Range: -5.4551

Max Act: 4.9819. Min Act: -0.1700

Data Index: 93982 (Open Web Text)

Max Activating Token Index: 460

Text #15

Max Range: 5.4551. Min Range: -5.4551

Max Act: 4.9767. Min Act: -0.1700

Data Index: 5621454 (Open Web Text)

Max Activating Token Index: 224

Text #16

Max Range: 5.4551. Min Range: -5.4551

Max Act: 4.9852. Min Act: -0.1700

Data Index: 7640827 (Open Web Text)

Max Activating Token Index: 779

Text #17

Max Range: 5.4551. Min Range: -5.4551

Max Act: 4.9689. Min Act: -0.1700

Data Index: 801729 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 5.4551. Min Range: -5.4551

Max Act: 4.9516. Min Act: -0.1700

Data Index: 4599353 (Open Web Text)

Max Activating Token Index: 427

Text #19

Max Range: 5.4551. Min Range: -5.4551

Max Act: 4.9390. Min Act: -0.1700

Data Index: 3528254 (Open Web Text)

Max Activating Token Index: 3