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

Dataset: Open Web Text

Neuron 224 in Layer 1

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: 0.8499. Min Range: -0.8499

Max Act: 0.8499. Min Act: -0.1699

Data Index: 8366684 (Open Web Text)

Max Activating Token Index: 40

Text #1

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8309. Min Act: -0.1700

Data Index: 4480956 (Open Web Text)

Max Activating Token Index: 480

Text #2

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8288. Min Act: -0.1700

Data Index: 8822504 (Open Web Text)

Max Activating Token Index: 99

Text #3

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.8060. Min Act: -0.1700

Data Index: 2613731 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7927. Min Act: -0.1700

Data Index: 8052057 (Open Web Text)

Max Activating Token Index: 775

Text #5

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7847. Min Act: -0.1700

Data Index: 7088402 (Open Web Text)

Max Activating Token Index: 988

Text #6

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7745. Min Act: -0.1700

Data Index: 857714 (Open Web Text)

Max Activating Token Index: 942

Text #7

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7775. Min Act: -0.1699

Data Index: 626193 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7727. Min Act: -0.1700

Data Index: 6932035 (Open Web Text)

Max Activating Token Index: 244

Text #9

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7647. Min Act: -0.1698

Data Index: 8121875 (Open Web Text)

Max Activating Token Index: 953

Text #10

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7682. Min Act: -0.1700

Data Index: 8731674 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7612. Min Act: -0.1700

Data Index: 747343 (Open Web Text)

Max Activating Token Index: 575

Text #12

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7649. Min Act: -0.1700

Data Index: 8420088 (Open Web Text)

Max Activating Token Index: 206

Text #13

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7582. Min Act: -0.1700

Data Index: 7064929 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7664. Min Act: -0.1700

Data Index: 8137011 (Open Web Text)

Max Activating Token Index: 485

Text #15

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7770. Min Act: -0.1700

Data Index: 5260357 (Open Web Text)

Max Activating Token Index: 601

Text #16

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7635. Min Act: -0.1700

Data Index: 7070050 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7564. Min Act: -0.1700

Data Index: 8284041 (Open Web Text)

Max Activating Token Index: 643

Text #18

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7604. Min Act: -0.1700

Data Index: 5332541 (Open Web Text)

Max Activating Token Index: 770

Text #19

Max Range: 0.8499. Min Range: -0.8499

Max Act: 0.7430. Min Act: -0.1700

Data Index: 2833162 (Open Web Text)

Max Activating Token Index: 351