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

Dataset: Open Web Text

Neuron 444 in Layer 6

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: 2.4599. Min Range: -2.4599

Max Act: 2.4599. Min Act: -0.1690

Data Index: 6067606 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3986. Min Act: -0.1700

Data Index: 3250376 (Open Web Text)

Max Activating Token Index: 615

Text #2

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3725. Min Act: -0.1700

Data Index: 7706293 (Open Web Text)

Max Activating Token Index: 654

Text #3

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3705. Min Act: -0.1699

Data Index: 3724121 (Open Web Text)

Max Activating Token Index: 228

Text #4

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3411. Min Act: -0.1648

Data Index: 1625949 (Open Web Text)

Max Activating Token Index: 401

Text #5

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3624. Min Act: -0.1700

Data Index: 3425383 (Open Web Text)

Max Activating Token Index: 530

Text #6

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3473. Min Act: -0.1697

Data Index: 1759953 (Open Web Text)

Max Activating Token Index: 316

Text #7

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3235. Min Act: -0.1617

Data Index: 2459246 (Open Web Text)

Max Activating Token Index: 879

Text #8

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3584. Min Act: -0.1698

Data Index: 6504908 (Open Web Text)

Max Activating Token Index: 910

Text #9

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3111. Min Act: -0.1469

Data Index: 4820077 (Open Web Text)

Max Activating Token Index: 199

Text #10

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3276. Min Act: -0.1700

Data Index: 3472145 (Open Web Text)

Max Activating Token Index: 340

Text #11

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3207. Min Act: -0.1695

Data Index: 722902 (Open Web Text)

Max Activating Token Index: 487

Text #12

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3120. Min Act: -0.1696

Data Index: 4298456 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.2958. Min Act: -0.1676

Data Index: 4385174 (Open Web Text)

Max Activating Token Index: 550

Text #14

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.3019. Min Act: -0.1677

Data Index: 2926831 (Open Web Text)

Max Activating Token Index: 962

Text #15

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.2747. Min Act: -0.1697

Data Index: 2571470 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.2731. Min Act: -0.1670

Data Index: 7123852 (Open Web Text)

Max Activating Token Index: 507

Text #17

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.2738. Min Act: -0.1699

Data Index: 5237745 (Open Web Text)

Max Activating Token Index: 811

Text #18

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.2936. Min Act: -0.1700

Data Index: 5319742 (Open Web Text)

Max Activating Token Index: 804

Text #19

Max Range: 2.4599. Min Range: -2.4599

Max Act: 2.2802. Min Act: -0.1699

Data Index: 5402908 (Open Web Text)

Max Activating Token Index: 868