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

Dataset: Open Web Text

Neuron 2518 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: 3.2513. Min Range: -3.2513

Max Act: 3.2513. Min Act: -0.1700

Data Index: 4184109 (Open Web Text)

Max Activating Token Index: 394

Text #1

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0764. Min Act: -0.1700

Data Index: 6897913 (Open Web Text)

Max Activating Token Index: 326

Text #2

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.1011. Min Act: -0.1700

Data Index: 3688750 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0333. Min Act: -0.1700

Data Index: 4576642 (Open Web Text)

Max Activating Token Index: 858

Text #4

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.1137. Min Act: -0.1700

Data Index: 7655788 (Open Web Text)

Max Activating Token Index: 465

Text #5

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0854. Min Act: -0.1700

Data Index: 3835390 (Open Web Text)

Max Activating Token Index: 44

Text #6

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0756. Min Act: -0.1700

Data Index: 7161837 (Open Web Text)

Max Activating Token Index: 445

Text #7

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.1239. Min Act: -0.1700

Data Index: 6613073 (Open Web Text)

Max Activating Token Index: 500

Text #8

Max Range: 3.2513. Min Range: -3.2513

Max Act: 2.9899. Min Act: -0.1700

Data Index: 7738680 (Open Web Text)

Max Activating Token Index: 811

Text #9

Max Range: 3.2513. Min Range: -3.2513

Max Act: 2.9976. Min Act: -0.1700

Data Index: 586753 (Open Web Text)

Max Activating Token Index: 517

Text #10

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0160. Min Act: -0.1700

Data Index: 8423508 (Open Web Text)

Max Activating Token Index: 551

Text #11

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0105. Min Act: -0.1700

Data Index: 3724755 (Open Web Text)

Max Activating Token Index: 56

Text #12

Max Range: 3.2513. Min Range: -3.2513

Max Act: 2.9984. Min Act: -0.1700

Data Index: 8716642 (Open Web Text)

Max Activating Token Index: 421

Text #13

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0379. Min Act: -0.1700

Data Index: 8638587 (Open Web Text)

Max Activating Token Index: 98

Text #14

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0436. Min Act: -0.1700

Data Index: 7935048 (Open Web Text)

Max Activating Token Index: 905

Text #15

Max Range: 3.2513. Min Range: -3.2513

Max Act: 2.9960. Min Act: -0.1700

Data Index: 3267721 (Open Web Text)

Max Activating Token Index: 634

Text #16

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0503. Min Act: -0.1700

Data Index: 3997257 (Open Web Text)

Max Activating Token Index: 384

Text #17

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0167. Min Act: -0.1700

Data Index: 4690467 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0192. Min Act: -0.1700

Data Index: 5902727 (Open Web Text)

Max Activating Token Index: 860

Text #19

Max Range: 3.2513. Min Range: -3.2513

Max Act: 3.0758. Min Act: -0.1700

Data Index: 8228899 (Open Web Text)

Max Activating Token Index: 443